Instructions to use moonbox-dev/HeartMuLa-oss-3B-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use moonbox-dev/HeartMuLa-oss-3B-MLX with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download moonbox-dev/HeartMuLa-oss-3B-MLX --local-dir HeartMuLa-oss-3B-MLX
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download bf16/quant.json from moonbox-dev/HeartMuLa-oss-3B-MLX: direct link, hf CLI and curl.
- Browser
- Download file 52 Bytes
-
https://huggingface.co/moonbox-dev/HeartMuLa-oss-3B-MLX/resolve/main/bf16/quant.json
- Command line
-
hf download hf://moonbox-dev/HeartMuLa-oss-3B-MLX/bf16/quant.json
-
curl -L -o quant.json https://huggingface.co/moonbox-dev/HeartMuLa-oss-3B-MLX/resolve/main/bf16/quant.json
52 Bytes
| {"quant": "bf16", "label": "bf16", "group_size": 64} |