vllm serve shawnw3i/Qwen3.8-27B-GPTQ-INT8-MTP \
--max-model-len 65536 \
--reasoning-parser qwen3 \
--speculative-config '{"method":"mtp","num_speculative_tokens":3}'
model-00005-of-00012.safetensors 3.2 GBmodel-00008-of-00012.safetensors 3.2 GBmodel-00004-of-00012.safetensors 3.2 GBmodel-00007-of-00012.safetensors 3.2 GBmodel-00001-of-00012.safetensors 3.1 GBmodel-00003-of-00012.safetensors 3.1 GBmodel-00006-of-00012.safetensors 3.1 GBmodel-00009-of-00012.safetensors 3.1 GBmodel-00002-of-00012.safetensors 3.1 GBmodel-00010-of-00012.safetensors 2.9 GBmodel-00011-of-00012.safetensors 2.5 GBmodel-00012-of-00012.safetensors 2.5 GBmodel_extra_tensors.safetensors 849 MBHave the files? Submit a torrent.
Submit a torrentHave 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 shawnw3i/Qwen3.8-27B-GPTQ-INT8-MTP ./model-folderQwen/Qwen3.8-27B