Instructions to use mlx-community/nanoLLaVA-1.5-3bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/nanoLLaVA-1.5-3bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download mlx-community/nanoLLaVA-1.5-3bit --local-dir nanoLLaVA-1.5-3bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download model.safetensors from mlx-community/nanoLLaVA-1.5-3bit: direct link, hf CLI and curl.
- Browser
- Download file 463 MB
-
https://huggingface.co/mlx-community/nanoLLaVA-1.5-3bit/resolve/5effde44a05aa2e3a42d20c6fdddceafe606819b/model.safetensors
- Command line
-
hf download hf://mlx-community/nanoLLaVA-1.5-3bit@5effde44a05aa2e3a42d20c6fdddceafe606819b/model.safetensors
-
curl -L -o model.safetensors https://huggingface.co/mlx-community/nanoLLaVA-1.5-3bit/resolve/5effde44a05aa2e3a42d20c6fdddceafe606819b/model.safetensors
463 MB
- Xet hash:
- dcbd496e1a6fed7def228a3a7cbdd03391651e079ff615473578d1ee330a942a
- Size of remote file:
- 463 MB
- SHA256:
- 1b6ad35f3c360da8e140b86c4609043188ad9785d65e603d0aa6f7a3bfa987b1
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.