How to use mlx-community/DeepSeek-R1-Distill-Qwen-7B-3bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download mlx-community/DeepSeek-R1-Distill-Qwen-7B-3bit --local-dir DeepSeek-R1-Distill-Qwen-7B-3bit
