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:
- 9f2f0ef317ae59d8c6054b8c3ab2ec0a1ef9d1f4b99d692a993b9d93d9b530b8
- Size of remote file:
- 4.45 GB
- SHA256:
- 808dbec8ac33f84e0eb5948a1426c5766f92ce2b3d541cb0dc400b366fb3f438
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.