How to use tfjack/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-oQ8-fp16-mtp with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-oQ8-fp16-mtp tfjack/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-oQ8-fp16-mtp
