How to use ndgold/Qwen3-0.6B-EasyLanguage-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3-0.6B-EasyLanguage-4bit ndgold/Qwen3-0.6B-EasyLanguage-4bit
ndgold commited on 