- IQ4F : IQ4_XS feed-forawrd (IQ4_NL for ffn_down due to shape constraints)
- Q8A : Q8_0 attention, Q8_0 output, Q8_0 embeds
- Q8SH : Q8_0 shared experts
Readable speeds on a 24GiB GPU + 64GB RAM w/ long context
Beinsezii/GLM-4.5-Air-Derestricted-IQ4F-Q8A-Q8SH-GGUF
Submit in one command
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/GLM-4.5-Air-Derestricted-IQ4F-Q8A-Q8SH-GGUF ./model-folder