MLX
Safetensors
qwen3_5_mtp
mlx-vlm
qwen3_5
qwen3.8
mtp
multi-token-prediction
speculative-decoding
self-speculation
draft-model
apple-silicon
Instructions to use intheblue/Qwen3.8-27B-AEON-Ultimate-Uncensored-MLX-MTP-Drafter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use intheblue/Qwen3.8-27B-AEON-Ultimate-Uncensored-MLX-MTP-Drafter with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3.8-27B-AEON-Ultimate-Uncensored-MLX-MTP-Drafter intheblue/Qwen3.8-27B-AEON-Ultimate-Uncensored-MLX-MTP-Drafter
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Ctrl+K