jedisct1

This is a GGUF quantized version of XiaomiMiMo/MiMo-7B-RL, optimized for use with llama.cpp, Ollama, LM Studio, and other GGUF-compatible inference engines. The model has been converted from the original SafeTensors format to GGUF. MiMo-7B-RL is a powerful 7B parameter language model developed by Xiaomi, specifically designed for enhanced reasoning capabilities in both mathematics and code. The original model matches the performance of OpenAI's o1-mini in many benchmarks. - Original Model: MiMo-7B-RL by Xiaomi - Parameters: 7 billion - Context Length: 32,768 tokens - Architecture: Modified transformer with 36 layers, 32 attention heads - Original Format: SafeTensors - Converted Format: GGUF - License: MIT - Trained using a specialized pre-training strategy focused on reasoning tasks - Fine-tuned with reinforcement learning on 130K mathematics and code problems - Demonstrates superior performance in both mathematical reasoning and coding tasks - Matches performance of much larger models in reasoning capabilities 1. Load the model through the LM Studio interface 2. Select the GGUF file 3. Configure your desired settings 4. Start chatting! The original model demonstrates impressive performance across various benchmarks: | Benchmark | Score | | ------------------------- | :---: | | MATH-500 (Pass@1) | 95.8% | | AIME 2024 (Pass@1) | 68.2% | | AIME 2025 (Pass@1) | 55.4% | | LiveCodeBench v5 (Pass@1) | 57.8% | | LiveCodeBench v6 (Pass@1) | 49.3% | Note: Performance metrics are from the original model. The GGUF conversion may show slightly different results due to quantization. The model inherits any limitations and biases present in the original MiMo-7B-RL model. Additionally: - Q8 quantization may result in slightly reduced performance compared to the original model - The model requires careful prompt engineering for optimal results in reasoning tasks - Performance may vary depending on the specific GGUF inference implementation used - Pre-training on approximately 25 trillion tokens - Three-stage data mixture strategy - Multiple-Token Prediction as an additional training objective - RL fine-tuning on 130K mathematics and code problems For detailed training information, please refer to the original model card. If you use this model, please cite the original work: Original model development by Xiaomi LLM-Core Team.

This model jedisct1/Qwen3-Coder-30B-A3B-Instruct-mlx was converted to MLX format from unsloth/Qwen3-Coder-30B-A3B-Instruct using mlx-lm version 0.26.2.

This model jedisct1/NextCoder-14B-q8-mlx was converted to MLX format from microsoft/NextCoder-14B using mlx-lm version 0.25.3.

This model jedisct1/NextCoder-32B-q8-mlx was converted to MLX format from microsoft/NextCoder-32B using mlx-lm version 0.25.3.

This model jedisct1/NextCoder-7B-q8-mlx was converted to MLX format from microsoft/NextCoder-14B using mlx-lm version 0.25.3.

This model jedisct1/NextCoder-32B-mlx was converted to MLX format from microsoft/NextCoder-32B using mlx-lm version 0.25.3.

This model jedisct1/reka-flash-3.1-8b-mlx was converted to MLX format from RekaAI/reka-flash-3.1 using mlx-lm version 0.25.3.