Instructions to use starkdmi/chatterbox-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use starkdmi/chatterbox-6bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir chatterbox-6bit starkdmi/chatterbox-6bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
| { | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 6 | |
| }, | |
| "precision": "int6" | |
| } |