GGUF. No quoted tok/s.
Params
31B
Fastest decode
—
Setups
0
Runs on
Quoted one-stream decode on real boxes.
No quoted pair yet.
Get it running
- 1. DownloadPuts the weights on this computer.
huggingface-cli download TrevorJS/gemma-4-31B-it-uncensored-GGUF - 2. Start itUse this only if the download is GGUF.
llama-server -hf TrevorJS/gemma-4-31B-it-uncensored-GGUF - Open the weightsHugging Face ↗