Instructions to use mlx-community/DeepSeek-V3-3bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/DeepSeek-V3-3bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir DeepSeek-V3-3bit mlx-community/DeepSeek-V3-3bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
Fix chat_template crash when assistant message omits the `content` key
#4 opened 10 days ago
by
qgallouedec
Required RAM to Run the Model
#3 opened over 1 year ago
by
wilfoderek