Instructions to use CuckmeisterFuller/Dolphin3.0-Qwen2.5-3b-Q8-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use CuckmeisterFuller/Dolphin3.0-Qwen2.5-3b-Q8-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Dolphin3.0-Qwen2.5-3b-Q8-mlx CuckmeisterFuller/Dolphin3.0-Qwen2.5-3b-Q8-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
File size: 135 Bytes
d9516db | 1 2 3 4 | version https://git-lfs.github.com/spec/v1
oid sha256:67252a098ce7a95270751ff1f444efcae2e68a5fe6c81f06007e31119eae867a
size 3279142142
|