How to use AlicanKiraz0/Qwen3.5-TurboQuant-MLX-LM with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3.5-TurboQuant-MLX-LM AlicanKiraz0/Qwen3.5-TurboQuant-MLX-LM
