How to use Kecven/Qwen3.8-27B-MTPLX-Q4 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3.8-27B-MTPLX-Q4 Kecven/Qwen3.8-27B-MTPLX-Q4
