How to use InferenceIllusionist/gpt-oss-20b-MLX-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir gpt-oss-20b-MLX-4bit InferenceIllusionist/gpt-oss-20b-MLX-4bit
