Converted to MLX format from huihui-ai/Huihui-Qwen3.8-27B-abliterated using mlx-vlm version 0.6.13.
Default reasoning_effort set to medium.
pip install -U mlx-vlm
python -m mlx_vlm.generate --model ailexleon/Huihui-Qwen3.8-27B-abliterated-mlx-8Bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
Have the files? Submit a torrent.
Submit a torrent →Have the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo ailexleon/Huihui-Qwen3.8-27B-abliterated-mlx-8Bit ./model-folder
LocalMaxxingomlx serve --model-dir ./models --host 127.0.0.1 --port 8036 --max-concurrent-requests 8 --memory-guard-gb 92 --no-cache --base-path ./baseView run on LocalMaxxing
Median of 2 community runs on 1 setups, from LocalMaxxing.
Run it yourself: setup guide