MLX
speculative-decoding
multi-token-prediction
mtp
apple-silicon
omlx
mtplx
qwen
qwen3.8
quantization
Instructions to use KaedeTai/mlx-mtp-graft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use KaedeTai/mlx-mtp-graft with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir mlx-mtp-graft KaedeTai/mlx-mtp-graft
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Welcome to the community
The community tab is the place to discuss and collaborate with the HF community!