Full GLM 5.3, not Flash. FP8. No quoted tok/s.
Params
753B
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 dealignai/GLM-5.3-UNCENSORED-FP8 - 2. Start itUse this only if the download is GGUF.
llama-server -hf dealignai/GLM-5.3-UNCENSORED-FP8 - Open the weightsHugging Face ↗