This model DeProgrammer/shisa-v2.1-qwen3-8b-MNN was converted to MNN format from shisa-ai/shisa-v2.1-qwen3-8b using llmexport.py in MNN version 3.4.0 with default settings (4-bit quantization).
Inference can be run via MNN, e.g., MNN Chat on Android.
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 DeProgrammer/shisa-v2.1-qwen3-8b-MNN ./model-folder