lmstudio-community

166,230

Qwen3-Coder-30B-A3B-Instruct-MLX-6bit

💫 Community Model> Qwen3-Coder-30B-A3B-Instruct by Qwen 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: Qwen Original model: Qwen3-Coder-30B-A3B-Instruct MLX quantization: provided by LM Studio team using mlxlm 6-bit quantized version of Qwen3-Coder-30B-A3B-Instruct using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

164,341

gemma-3n-E4B-it-MLX-4bit

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: google Original model: gemma-3n-E4B-it MLX quantization: provided by LM Studio team using mlxvlm 4-bit quantized version of gemma-3n-E4B-it using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

163,236

gemma-3n-E4B-it-MLX-bf16

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: NousResearch Original model: Hermes-4-70B MLX quantization: provided by LM Studio team using mlxlm 6-bit quantized version of Hermes-4-70B using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

llama

59,420

Qwen3-30B-A3B-Instruct-2507-MLX-4bit

58,182

💫 Community Model> Magistral-Small-2509 by mistralai 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: mistralai Original model: Magistral-Small-2509 GGUF quantization: provided by LM Studio team using `llama.cpp` release b6503 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

52,631

gemma-3-12b-it-GGUF

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: google Original model: gemma-3-12b-it GGUF quantization: provided by bartowski based on `llama.cpp` release b4877 Supports a context length of 128k tokens, with a max output of 8192. Multimodal supporting images normalized to 896 x 896 resolution. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Requires latest (currently beta) llama.cpp runtime. 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

52,269

Qwen3-VL-8B-Instruct-GGUF

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: Qwen Original model: Qwen3-VL-8B-Instruct GGUF quantization: provided by LM Studio team using `llama.cpp` release b6890 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

42,526

Qwen2.5-VL-7B-Instruct-GGUF

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: Qwen Original model: Qwen2.5-VL-7B-Instruct GGUF quantization: provided by bartowski based on `llama.cpp` release b5317 Proficient in recognizing common objects such as flowers, birds, fish, and insects, but it is highly capable of analyzing texts, charts, icons, graphics, and layouts within images. Capable of acting as a visual agent that can reason and dynamically direct tools, which is capable of computer use and phone use. Useful for generating structured outputs and stable JSON outputs. 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

40,047

Qwen2.5-Coder-14B-Instruct-MLX-8bit

39,163

Qwen3-VL-30B-A3B-Instruct-GGUF

💫 Community Model> Qwen3-VL-30B-A3B-Instruct by Qwen 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: Qwen Original model: Qwen3-VL-30B-A3B-Instruct GGUF quantization: provided by LM Studio team using `llama.cpp` release b6890 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Compatibility: Apple Silicon Macs Model creator: Qwen Original model: QwQ-32B MLX quantizations: provided by bartowski from mlx-examples LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

ERNIE-4.5-21B-A3B-MLX-6bit

29,840

gemma-3-4b-it-GGUF

27,428

gemma-3n-E4B-it-text-GGUF

27,061

granite-4.0-h-tiny-GGUF

26,924

GLM-4.6V-Flash-MLX-4bit

26,733

Phi-4-reasoning-plus-MLX-4bit

Qwen3-4B-MLX-4bit

This model lmstudio-community/Qwen3-4B-MLX-4bit was converted to MLX format from Qwen/Qwen3-4B using mlx-lm version 0.24.0.

18,986

Qwen2.5-Coder-32B-Instruct-MLX-4bit

💫 Community Model> Qwen2.5 Coder 32B Instruct by Qwen 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Compatibility: Apple Silicon Macs Model creator: Qwen Original model: Qwen2.5-Coder-32B-Instruct MLX quantizations: provided by bartowski from mlx-examples Long-context Support up to 128K tokens with yarn rope scaling factor of 4.0 Up to 5.5 trillion training tokens including source code, text-code grounding, and synthetic data LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

18,721

Qwen3-4B-MLX-8bit

This model lmstudio-community/Qwen3-4B-MLX-8bit was converted to MLX format from Qwen/Qwen3-4B using mlx-lm version 0.24.0.

Mistral-Small-3.2-24B-Instruct-2506-GGUF

💫 Community Model> Mistral Small 3.2 24B Instruct 2506 by Mistralai 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: mistralai Original model: Mistral-Small-3.2-24B-Instruct-2506 GGUF quantization: provided by lmmy based on `llama.cpp` release b5726 Supports dozens of languages, including English, French, German, Spanish, Portuguese, Italian, Japanese, Korean, Russian, Chinese, Arabic, Persian, Indonesian, Malay, Nepali, Polish, Romanian, Serbian, Swedish, Turkish, Ukrainian, Vietnamese, Hindi, and Bengali. This model's tool calling performance may be degraded. Stay tuned for more updates from the team. 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

10,942

phi-4-GGUF

10,531

Qwen2.5-Coder-14B-Instruct-GGUF

10,240

Phi-4-mini-reasoning-GGUF

10,216

Seed-OSS-36B-Instruct-GGUF

💫 Community Model> Seed-OSS-36B-Instruct by ByteDance-Seed 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: ByteDance-Seed Original model: Seed-OSS-36B-Instruct GGUF quantization: provided by LM Studio team using `llama.cpp` release b6292 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

9,333

DeepSeek-Coder-V2-Lite-Instruct-GGUF

9,126

Meta-Llama-3-8B-Instruct-GGUF

Codestral-22B-v0.1-GGUF

7,681

Qwen3-32B-GGUF

7,470

GLM-4.5-Air-MLX-8bit

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: zai-org Original model: GLM-4.5-Air MLX quantization: provided by LM Studio team using mlxlm 8-bit quantized version of GLM-4.5-Air using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

7,372

Qwen3-4B-GGUF

7,076

NVIDIA-Nemotron-3-Nano-30B-A3B-GGUF

Qwen3-235B-A22B-Instruct-2507-MLX-8bit

5,918

Qwen3-Coder-480B-A35B-Instruct-MLX-8bit

5,839

Mistral-Nemo-Instruct-2407-GGUF

5,621

SmolLM2-1.7B-Instruct-GGUF

5,325

Qwen3-0.6B-GGUF

gemma-2-9b-it-GGUF

4,301

Qwen3-30B-A3B-GGUF

4,046

gemma-3-270m-it-MLX-8bit

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: google Original model: gemma-3-270m-it MLX quantization: provided by LM Studio team using mlxlm 8-bit quantized version of gemma-3-270m-it using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

3,993

Llama-3.1-Tulu-3-8B-GGUF

base_model:allenai/Llama-3.1-Tulu-3-8B

3,740

EXAONE-3.5-2.4B-Instruct-GGUF

3,616

Qwen3-Coder-Next-GGUF

3,571

Yi-Coder-1.5B-GGUF

3,548

gemma-3-4B-it-qat-GGUF

3,546

EXAONE-3.5-7.8B-Instruct-GGUF

3,532

OpenCoder-1.5B-Instruct-GGUF

3,516

gpt-oss-safeguard-20b-MLX-MXFP4

💫 Community Model> gpt-oss-safeguard-20b by openai 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: openai Original model: gpt-oss-safeguard-20b MLX quantization: provided by LM Studio team using mlxlm MXFP4 quantized version of gpt-oss-safeguard-20b using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

gemma-3-1b-it-GGUF

3,045

Qwen2.5-Coder-32B-GGUF

2,967

DeepSeek-R1-Distill-Qwen-1.5B-GGUF

2,914

granite-4.0-h-small-MLX-8bit

💫 Community Model> granite-4.0-h-small by ibm-granite 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: ibm-granite Original model: granite-4.0-h-small MLX quantization: provided by LM Studio team using mlxlm 8-bit quantized version of granite-4.0-h-small using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

💫 Community Model> gpt-oss-safeguard-20b by openai 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: openai Original model: gpt-oss-safeguard-20b GGUF quantization: provided by LM Studio team using `llama.cpp` release b6868 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

2,411

Qwen2.5-Coder-7B-Instruct-GGUF

2,397

gemma-2-27b-it-GGUF

2,312

GLM-4.5-Air-MLX-4bit

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: zai-org Original model: GLM-4.5-Air MLX quantization: provided by LM Studio team using mlxlm 4-bit quantized version of GLM-4.5-Air using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

2,289

GLM-4.5-Air-GGUF

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: zai-org Original model: GLM-4.5-Air GGUF quantization: provided by bartowski based on `llama.cpp` release b6085 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

2,278

embeddinggemma-300m-qat-GGUF

1,389

Qwen2.5-VL-32B-Instruct-GGUF

💫 Community Model> Qwen2.5 VL 32B Instruct by Qwen 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: Qwen Original model: Qwen2.5-VL-32B-Instruct GGUF quantization: provided by bartowski based on `llama.cpp` release b5284 Proficient in recognizing common objects such as flowers, birds, fish, and insects, but it is highly capable of analyzing texts, charts, icons, graphics, and layouts within images. Capable of acting as a visual agent that can reason and dynamically direct tools, which is capable of computer use and phone use. Useful for generating structured outputs and stable JSON outputs. 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

1,366

granite-4.0-h-small-GGUF

1,327

gemma-3n-E2B-it-text-GGUF

1,325

Qwen3-0.6B-MLX-4bit

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: Qwen Original model: Qwen3-0.6B MLX quantization: provided by LM Studio team using mlxlm 4-bit quantized version of Qwen3-0.6B using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

1,309

granite-4.0-h-tiny-MLX-8bit

1,279

Qwen2.5-7B-Instruct-GGUF

1,278

Mistral-Small-3.1-24B-Instruct-2503-GGUF

1,269

Qwen3-Coder-480B-A35B-Instruct-GGUF

💫 Community Model> Qwen3 Coder 480B A35B Instruct by Qwen 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: Qwen Original model: Qwen3-Coder-480B-A35B-Instruct GGUF quantization: provided by bartowski based on `llama.cpp` release b5962 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

1,259

Phi-4-mini-instruct-GGUF

1,228

Qwen3-VL-2B-Instruct-MLX-8bit

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: Qwen Original model: Qwen3-VL-2B-Instruct MLX quantization: provided by LM Studio team using mlxvlm LM Studio model page: Qwen3-VL 8-bit quantized version of Qwen3-VL-2B-Instruct using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

1,212

medgemma-27b-text-it-MLX-4bit

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: google Original model: medgemma-27b-text-it MLX quantization: provided by LM Studio team using mlxlm 4-bit quantized version of medgemma-27b-text-it using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

1,082

Phi-3.1-mini-4k-instruct-GGUF

992

Qwen3-235B-A22B-GGUF

992

Qwen3-VL-32B-Thinking-GGUF

DeepSeek-Coder-V2-Instruct-0724-GGUF

856

Qwen3-VL-32B-Instruct-MLX-4bit

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: Qwen Original model: Qwen3-VL-32B-Instruct MLX quantization: provided by LM Studio team using mlxvlm LM Studio model page: Qwen3-VL 4-bit quantized version of Qwen3-VL-32B-Instruct using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

846

Llama-4-Scout-17B-16E-MLX-text-8bit

llama4

843

gemma-3-270m-it-MLX-bf16

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: google Original model: gemma-3-270m-it MLX quantization: provided by LM Studio team using mlxlm Original bfloat16 version of gemma-3-270m-it using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

817

Qwen2.5-14B-Instruct-1M-GGUF

💫 Community Model> Qwen2.5 14B Instruct 1M by Qwen 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: Qwen Original model: Qwen2.5-14B-Instruct-1M GGUF quantization: provided by bartowski based on `llama.cpp` release b4546 Significantly improved performance in handling long-context tasks while maintaining its capability in short tasks. Accuracy degradation may occur for sequences exceeding 262,144 tokens until improved support is added. 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

801

codegemma-7b-it-GGUF

787

Qwen3-0.6B-MLX-bf16

InternVL3_5-14B-GGUF

766

Qwen2-VL-7B-Instruct-GGUF

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: Qwen Original model: Qwen2-VL-7B-Instruct GGUF quantization: provided by bartowski based on `llama.cpp` release b4327 Vision model capable of understanding images of various resolutions and ratios. Complex reasoning for agentic automation with vision. 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

756

Qwen3-Next-80B-A3B-Thinking-MLX-4bit

726

gemma-3-270m-it-qat-GGUF

💫 Community Model> gemma-3-270m-it-qat-q40 by google 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: google Original model: gemma-3-270m-it-qat-q40-unquantized GGUF quantization: provided by LM Studio team using `llama.cpp` release b6153 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

725

granite-4.0-h-micro-GGUF

719

Qwen2.5-Coder-7B-Instruct-MLX-8bit

💫 Community Model> Qwen2.5 Coder 7B Instruct by Qwen 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Compatibility: Apple Silicon Macs Model creator: Qwen Original model: Qwen2.5-Coder-7B-Instruct MLX quantizations: provided by bartowski from mlx-examples Long-context Support up to 128K tokens with yarn rope scaling factor of 4.0 Up to 5.5 trillion training tokens including source code, text-code grounding, and synthetic data LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

716

Qwen3-Next-80B-A3B-Thinking-GGUF

692

Qwen2.5-Coder-1.5B-Instruct-GGUF

687

GLM-4-9B-0414-GGUF

679

InternVL3_5-30B-A3B-GGUF

💫 Community Model> InternVL35 30B A3B by Opengvlab 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: OpenGVLab Original model: InternVL35-30B-A3B GGUF quantization: provided by bartowski based on `llama.cpp` release b6258 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

Qwen2-VL-2B-Instruct-GGUF

592

GLM-4-32B-0414-GGUF

Qwen3-VL-32B-Thinking-MLX-8bit

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: Qwen Original model: Qwen3-VL-32B-Thinking MLX quantization: provided by LM Studio team using mlxvlm 8-bit quantized version of Qwen3-VL-32B-Thinking using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

506

Qwen2.5-Coder-1.5B-Instruct-MLX-8bit

💫 Community Model> Qwen2.5 Coder 1.5B Instruct by Qwen 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Compatibility: Apple Silicon Macs Model creator: Qwen Original model: Qwen2.5-Coder-1.5B-Instruct MLX quantizations: provided by bartowski from mlx-examples Up to 5.5 trillion training tokens including source code, text-code grounding, and synthetic data LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

503

Qwen3-30B-A3B-Thinking-2507-MLX-6bit

493

Qwen3-235B-A22B-Thinking-2507-GGUF

💫 Community Model> Qwen3 235B A22B Thinking 2507 by Qwen 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: Qwen Original model: Qwen3-235B-A22B-Thinking-2507 GGUF quantization: provided by bartowski based on `llama.cpp` release b5962 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

Qwen2-500M-Instruct-GGUF

468

Qwen3-235B-A22B-Thinking-2507-MLX-8bit

💫 Community Model> Qwen3-235B-A22B-Thinking-2507 by Qwen 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: Qwen Original model: Qwen3-235B-A22B-Thinking-2507 MLX quantization: provided by LM Studio team using mlxlm 8-bit quantized version of Qwen3-235B-A22B-Thinking-2507 using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

466

InternVL3_5-8B-GGUF

465

Yi-Coder-9B-Chat-GGUF

463

MiniCPM-o-2_6-GGUF

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: openbmb Original model: MiniCPM-o-26 GGUF quantization: provided by bartowski based on `llama.cpp` release b4585 Supports images of any aspect ratio up to 1.8 million pixels (e.g. 1344x1344) See more in their technical report (here)[https://openbmb.notion.site/MiniCPM-o-2-6-A-GPT-4o-Level-MLLM-for-Vision-Speech-and-Multimodal-Live-Streaming-on-Your-Phone-185ede1b7a558042b5d5e45e6b237da9] 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

454

codegemma-7b-GGUF

454

codegemma-1.1-7b-it-GGUF

449

deepseek-coder-1.3B-kexer-GGUF

438

Qwen3-VL-2B-Thinking-GGUF

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: Qwen Original model: Qwen3-VL-2B-Thinking GGUF quantization: provided by LM Studio team using `llama.cpp` release b6889 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

435

gemma-1.1-2b-it-GGUF

432

LFM2-350M-MLX-8bit

421

SmolLM3-3B-MLX-8bit

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: HuggingFaceTB Original model: SmolLM3-3B MLX quantization: provided by LM Studio team using mlxlm 8-bit quantized version of SmolLM3-3B using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

415

Qwen2.5-Coder-0.5B-Instruct-GGUF

412

Qwen3-VL-32B-Instruct-MLX-5bit

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: Qwen Original model: Qwen3-VL-32B-Instruct MLX quantization: provided by LM Studio team using mlxvlm LM Studio model page: Qwen3-VL 5-bit quantized version of Qwen3-VL-32B-Instruct using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

412

granite-embedding-107m-multilingual-GGUF

InternVL3_5-2B-GGUF

359

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: google Original model: gemma-3-270m-it MLX quantization: provided by LM Studio team using mlxlm 4-bit quantized version of gemma-3-270m-it using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

345

LFM2-VL-1.6B-GGUF

341

GLM-4.5-GGUF

341

medgemma-4b-it-MLX-4bit

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: google Original model: medgemma-4b-it MLX quantization: provided by LM Studio team using mlxlm 4-bit quantized version of medgemma-4b-it using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

339

Qwen2.5-32B-Instruct-GGUF

336

granite-embedding-278m-multilingual-GGUF

324

granite-4.0-h-tiny-MLX-4bit

323

stable-code-instruct-3b-GGUF

322

gemma-3n-E2B-it-MLX-4bit

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: google Original model: gemma-3n-E2B-it MLX quantization: provided by LM Studio team using mlxvlm 4-bit quantized version of gemma-3n-E2B-it using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

320

GLM-Z1-9B-0414-GGUF

315

KAT-Dev-GGUF

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: Kwaipilot Original model: KAT-Dev GGUF quantization: provided by LM Studio team using `llama.cpp` release b6644 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

315

OREAL-DeepSeek-R1-Distill-Qwen-7B-GGUF

305

aya-expanse-8b-GGUF

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: CohereForAI Original model: aya-expanse-8b GGUF quantization: provided by bartowski based on `llama.cpp` release b3930 Aya Expanse offers highly advanced multilingual capabilities. License: CC-BY-NC, requires also adhering to C4AI's Acceptable Use Policy Supports 23 languages: Arabic, Chinese (simplified & traditional), Czech, Dutch, English, French, German, Greek, Hebrew, Hebrew, Hindi, Indonesian, Italian, Japanese, Korean, Persian, Polish, Portuguese, Romanian, Russian, Spanish, Turkish, Ukrainian, and Vietnamese 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

license:cc-by-nc-4.0

297

aya-23-8B-GGUF

license:cc-by-nc-4.0

296

Starling-LM-7B-beta-GGUF

289

Qwen2.5-Math-7B-Instruct-GGUF

288

Meta-Llama-3-120B-Instruct-GGUF

base_model:mlabonne/Meta-Llama-3-120B-Instruct

286

SmolLM2-135M-Instruct-GGUF

285

Qwen2.5-Coder-3B-Instruct-GGUF

283

internlm2-math-plus-20b-GGUF

281

Qwen3-235B-A22B-Thinking-2507-MLX-4bit

💫 Community Model> Qwen3-235B-A22B-Thinking-2507 by Qwen 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: Qwen Original model: Qwen3-235B-A22B-Thinking-2507 MLX quantization: provided by LM Studio team using mlxlm 4-bit quantized version of Qwen3-235B-A22B-Thinking-2507 using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

Yi-1.5-6B-Chat-GGUF

241

EXAONE-4.0-1.2B-GGUF

239

LFM2-VL-450M-GGUF

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: LiquidAI Original model: LFM2-VL-450M GGUF quantization: provided by bartowski based on `llama.cpp` release b6214 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

239

UI-TARS-7B-DPO-GGUF

Qwen2.5-Coder-3B-Instruct-MLX-8bit

212

Meta-Llama-3-8B-Instruct-BPE-fix-GGUF

llama

210

c4ai-command-r-plus-08-2024-GGUF

cogito-v2-preview-llama-109B-MoE-GGUF

💫 Community Model> cogito v2 preview llama 109B MoE by Deepcogito 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: deepcogito Original model: cogito-v2-preview-llama-109B-MoE GGUF quantization: provided by bartowski based on `llama.cpp` release b6014 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

171

OlympicCoder-32B-GGUF

170

Qwen2.5-7B-Instruct-MLX-8bit

170

Hunyuan-A13B-Instruct-GGUF

DeepSeek-V2.5-1210-GGUF

156

SmolLM2-360M-Instruct-GGUF

LFM2-350M-MLX-bf16

143

💫 Community Model> granite embedding 30m english by Ibm-Granite 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: ibm-granite Original model: granite-embedding-30m-english GGUF quantization: provided by bartowski based on `llama.cpp` release b4381 30 million param model for extremely fast performance 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

134

Qwen2-Math-72B-Instruct-GGUF

130

Qwen2.5-Coder-3B-GGUF

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: NousResearch Original model: Hermes-4-405B GGUF quantization: provided by LM Studio team using `llama.cpp` release b6292 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

license:llama3

114

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: NousResearch Original model: Hermes-4-405B MLX quantization: provided by LM Studio team using mlxlm 4-bit quantized version of Hermes-4-405B using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

llama

103

OpenThinker3-7B-GGUF

llama-factory

102

Qwen2.5-0.5B-Instruct-MLX-8bit

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Compatibility: Apple Silicon Macs Model creator: Qwen Original model: Qwen2.5-0.5B-Instruct MLX quantizations: provided by bartowski from mlx-examples Long context: Support for 32k tokens and 8k token generation Large-scale training dataset: Encompasses a huge range of knowledge. Enhanced structured data understanding and generation. Over 29 languages including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, and Arabic. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

102

DeepSWE-Preview-GGUF

💫 Community Model> DeepSWE Preview by Agentica-Org 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: agentica-org Original model: DeepSWE-Preview GGUF quantization: provided by bartowski based on `llama.cpp` release b5760 Trained on top of Qwen3-32B with thinking mode enabled Coding agent trained with only reinforcement learning (RL) to excel at software engineering (SWE) tasks Achieves an impressive 59.0% on SWE-Bench-Verified, which is currently #1 in the open-weights category 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

100

Qwen3-VL-8B-Thinking-MLX-8bit

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: Qwen Original model: Qwen3-VL-8B-Thinking MLX quantization: provided by LM Studio team using mlxvlm LM Studio model page: Qwen3-VL 8-bit quantized version of Qwen3-VL-8B-Thinking using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

💫 Community Model> DeepSeek R1 0528 by Deepseek-Ai 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: deepseek-ai Original model: DeepSeek-R1-0528 GGUF quantization: provided by bartowski based on `llama.cpp` release b5524 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

Skywork-R1V3-38B-GGUF

openhands-lm-32b-v0.1-GGUF

Llama-3.1-Tulu-3-70B-GGUF

base_model:allenai/Llama-3.1-Tulu-3-70B

Qwen3-VL-30B-A3B-Thinking-MLX-4bit

Qwen3-VL-32B-Thinking-MLX-5bit

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: Qwen Original model: Qwen3-VL-32B-Thinking MLX quantization: provided by LM Studio team using mlxvlm 5-bit quantized version of Qwen3-VL-32B-Thinking using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

Qwen2.5-Coder-0.5B-GGUF

cogito-v1-preview-qwen-32B-GGUF

AceReason-Nemotron-1.1-7B-GGUF

💫 Community Model> AceReason Nemotron 1.1 7B by Nvidia 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: nvidia Original model: AceReason-Nemotron-1.1-7B GGUF quantization: provided by bartowski based on `llama.cpp` release b5674 Thanks to its stronger SFT backbone, AceReason-Nemotron-1.1-7B significantly outperforms its predecessor and sets a record-high performance among Qwen2.5-7B-based reasoning models on challenging math and code reasoning benchmarks Technical report available here: https://arxiv.org/abs/2506.13284 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

Falcon3-7B-Instruct-GGUF

SmolLM3-3B-MLX-4bit

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: HuggingFaceTB Original model: SmolLM3-3B MLX quantization: provided by LM Studio team using mlxlm 4-bit quantized version of SmolLM3-3B using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

LFM2-700M-MLX-8bit

Yi-Coder-1.5B-Chat-GGUF

cogito-v1-preview-llama-8B-GGUF

base_model:deepcogito/cogito-v1-preview-llama-8B

EXAONE-4.0-1.2B-MLX-4bit

OlympicCoder-7B-GGUF

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: open-r1 Original model: OlympicCoder-7B GGUF quantization: provided by bartowski based on `llama.cpp` release b4867 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

Qwen3-VL-30B-A3B-Thinking-MLX-6bit

OpenCoder-8B-Instruct-GGUF

Qwen2.5-1.5B-Instruct-MLX-8bit

OpenReasoning-Nemotron-32B-GGUF

💫 Community Model> OpenReasoning Nemotron 32B by Nvidia 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: nvidia Original model: OpenReasoning-Nemotron-32B GGUF quantization: provided by bartowski based on `llama.cpp` release b5934 🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

AM-Thinking-v1-GGUF

LFM2-700M-MLX-bf16

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: NousResearch Original model: Hermes-4-405B MLX quantization: provided by LM Studio team using mlxlm 6-bit quantized version of Hermes-4-405B using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

💫 Community Model> Magistral-Small-2507 by mistralai 👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: mistralai Original model: Magistral-Small-2507 MLX quantization: provided by LM Studio team using mlxlm 8-bit quantized version of Magistral-Small-2507 using MLX, optimized for Apple Silicon. 🙏 Special thanks to the Apple Machine Learning Research team for creating MLX. LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

Qwen3-VL-4B-Thinking-MLX-4bit