6.11 bpw, a mixture of Q6_K and Q5_K_M
Fits ~32k CTX + MMPROJ on a 24GiB GPU
Run it next to your model folder. It makes the torrent, checks your files against Hugging Face, and submits it. You just start seeding and paste your key from your account. It only reads your files and never changes them. Read the script first if you like.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo Beinsezii/Qwen3.5-27B-6.11BPW-GGUF ./model-folder6.11 bpw, a mixture of Q6_K and Q5_K_M
Fits ~32k CTX + MMPROJ on a 24GiB GPU