Duplicated from aufklarer/Qwen3-ASR-0.6B-MLX-4bit
How to use aitytech/Qwen3-ASR-0.6B-MLX-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3-ASR-0.6B-MLX-4bit aitytech/Qwen3-ASR-0.6B-MLX-4bit
