Duplicated from aufklarer/Qwen3-ASR-1.7B-MLX-8bit
How to use aitytech/Qwen3-ASR-1.7B-MLX-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3-ASR-1.7B-MLX-8bit aitytech/Qwen3-ASR-1.7B-MLX-8bit
