How to use brainworkup/Llama-3.1-8B-oQ8 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Llama-3.1-8B-oQ8 brainworkup/Llama-3.1-8B-oQ8
brainworkup commited on 