Skip to content

Instantly share code, notes, and snippets.

@voxels
Created May 22, 2026 15:31
Show Gist options
  • Select an option

  • Save voxels/0aa591a119782bb806b6f803a57c8e87 to your computer and use it in GitHub Desktop.

Select an option

Save voxels/0aa591a119782bb806b6f803a57c8e87 to your computer and use it in GitHub Desktop.
Install Qwen 3.6
conda create -n qwen python=3.11 -y
conda activate qwen
pip install mlx-lm
python -m mlx_lm server --model unsloth/Qwen3.6-35B-A3B-UD-MLX-4bit --port 8000 --max-tokens 16384 --prompt-concurrency 2048 --decode-concurrency 1 --prompt-cache-bytes 45G --trust-remote-code
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment