Safetensors
MLX
English
mlx-lm
minimax_m2
quantization
mixed_3_6
minimax
custom_code
4-bit precision
Instructions to use petergilani/MiniMax-M2.5-mix3-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use petergilani/MiniMax-M2.5-mix3-6bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir MiniMax-M2.5-mix3-6bit petergilani/MiniMax-M2.5-mix3-6bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Xet hash:
- 61b4dde6a12b074cd6ae52eef2962b7eca485af7dcda382423a2878bd96a8717
- Size of remote file:
- 15.5 MB
- SHA256:
- 7b81e5e5cba2b169e86a0771825a927e9d41b4c4484ded4a286410f41f702f17
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.