Reinforcement Learning
MLX
Safetensors
English
Chinese
qwen3_5
CUDA
MUSA
GPU-Kernel
Reinforcement-Learning
mlx-my-repo
4-bit precision
Instructions to use cnfusion/MusaCoder-27B-mlx-4Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use cnfusion/MusaCoder-27B-mlx-4Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir MusaCoder-27B-mlx-4Bit cnfusion/MusaCoder-27B-mlx-4Bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
- Xet hash:
- 84aab2449bd46520d469b626bb102d57db07e8fb70b58e101a0b540f29090ffa
- Size of remote file:
- 5.33 GB
- SHA256:
- a18eec9dfb5568d1edc1e5b78078010c092514544e68e541e98b007e6ea18a1f
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.