How to use majentik/Qwen3-ASR-0.6B-MLX-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3-ASR-0.6B-MLX-8bit majentik/Qwen3-ASR-0.6B-MLX-8bit
majentik commited on 