How to use m-i/KAT-Dev-72B-Exp-mlx-8Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir KAT-Dev-72B-Exp-mlx-8Bit m-i/KAT-Dev-72B-Exp-mlx-8Bit