How to use RolanDorisTech/Qwen3.8-2B-Distill-MLX-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download RolanDorisTech/Qwen3.8-2B-Distill-MLX-4bit --local-dir Qwen3.8-2B-Distill-MLX-4bit
