How to use mlx-community/Qwen3.5-4B-MLX-bf16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3.5-4B-MLX-bf16 mlx-community/Qwen3.5-4B-MLX-bf16
https://huggingface.co/mlx-community/Qwen3.5-4B-MLX-bf16/resolve/main/vocab.json
hf download hf://mlx-community/Qwen3.5-4B-MLX-bf16/vocab.json
curl -L -o vocab.json https://huggingface.co/mlx-community/Qwen3.5-4B-MLX-bf16/resolve/main/vocab.json
