How to use ddalcu/Qwen-Image-2.1-MLX-Serve-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen-Image-2.1-MLX-Serve-4bit ddalcu/Qwen-Image-2.1-MLX-Serve-4bit
