ngxson
Vintern-1B-v3_5-GGUF
--- license: mit base_model: - 5CD-AI/Vintern-1B-v3_5 ---
GLM-4.7-Flash-GGUF
Home-Cook-Mistral-Small-Omni-24B-2507-GGUF
This is a multimodal model created by merging Mistral Small 2506 (with vision capabilities) and Voxtral 2507 (with audio capabilities) using a modified version of the `mergekit` tool. For detailed merging instructions, refer to the sections below. This model is a merged derivative work combining Mistral Small 2506 and Voxtral 2507, both originally released by Mistral AI under the Apache 2.0 license. The merged model is also distributed under the Apache 2.0 license, and the full license text, along with original copyright notices, is included in this repository. I have no affiliation, sponsorship, or formal relationship with Mistral AI. This project is an independent effort to combine the vision and audio capabilities of the two models. Install `mergekit` from this version: https://github.com/arcee-ai/mergekit/tree/0027c5c51471fa891d438eccda5455ebe55b536e Modify the `mergekit` source code, open file `mergekit/mergemethods/generalizedtaskarithmetic.py` Go to the `mistralo` output directory, then download `tekken.json` from Voxtral and place it there: https://huggingface.co/mistralai/Voxtral-Small-24B-2507/blob/main/tekken.json Finally, use `converthftogguf.py` to convert it back to GGUF as usual Download these mmproj files: - Audio: https://huggingface.co/ggml-org/Voxtral-Mini-3B-2507-GGUF/blob/main/mmproj-Voxtral-Mini-3B-2507-Q80.gguf - Vision: https://huggingface.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF/blob/main/mmproj-F16.gguf Rename them to `audio.gguf`and `vision.gguf` respectively Then run mergemmprojmodels.py from this repo. The output file will be `mmproj-model.gguf`
boring-testing-tiny
DeepSeek-R1-Distill-Qwen-7B-abliterated-GGUF
test_gguf_models
Devstral-Small-Vision-2505-GGUF
The vision encoder is taken from Mistral Small, works out-of-the-box with llama.cpp
test_gguf_lora_adapter
wllama-split-models
tinyllama_split_test
SmolLM2-1.7B-Instruct-Q4_K_M-GGUF
gemma-3-mmproj-gguf-q8_0-TEST
Vistral-7B-ChatML
LFM2-VL-450M-GGUF-Q4_0
MiMo-VL-7B-RL-GGUF
Original model: https://huggingface.co/XiaomiMiMo/MiMo-VL-7B-RL
test-model-preset
ultravox-wip-ggml-do-not-use
DeepSeek-R1-Remixed-IQ1_M
LFM2-test-ci-80M
Llama-3-Instruct-abliteration-LoRA-8B-F16-GGUF
MiniThinky-v2-1B-Llama-3.2-Q8_0-GGUF
vistral-meow
Qwen2.5-7B-Instruct-1M-Q4_K_M-GGUF
qwen3_next_fixed
Meta-Llama-3.1-8B-Instruct-Q8_0
gemma-3-4b-pt-Q4_0-GGUF
Meta-Llama-3.1-8B-Instruct-Q4_K_M-GGUF
Llama-4-Scout-17B-16E-Instruct-GGUF
GLM-5-small-test
MiniThinky-1B-Llama-3.2-Q8_0-GGUF
Llama-4-Maverick-17B-128E-Instruct-Q2_K-GGUF
hunyuan-moe-tiny-random
SmolLM2-135M-Instruct-IQ4_XS-GGUF
Llama-3.2-1B-Creative-Lora-F16-GGUF
test-gemma-2-2b-gguf
tinygemma3_cifar
test-llava-will-be-deleted-soon
LoRA-Hermes-3-Llama-3.1-8B-F16-GGUF
TEST-Tiny-Llama4
demo_simple_rag_py
LoRA-phi-4-abliterated
This is a LoRA extracted from a language model. It was extracted using mergekit. This LoRA adapter was extracted from huihui-ai/phi-4-abliterated and uses microsoft/phi-4 as a base. The following command was used to extract this LoRA adapter: