RadixArk releases experimental NVFP4 checkpoint for GLM-5.3
Original titleGLM-5.2 on SGLang was battle-tested and is currently serving hundreds of thousands of people in production with our partners. GLM-5.3 car...
AISummary
RadixArk has published an experimental NVFP4 checkpoint for Zhipu's GLM-5.3 on Hugging Face, and says Miles support for GLM-5.3 is on the way.
The company says GLM-5.2 is already serving hundreds of thousands of people in production with its partners on SGLang.
Background from SGLang reports day-0 serving support for GLM-5.3, with 537.6 tok/s/user on NVFP4 and 413 tok/s/user on FP8 at BS=1 with TP8 on 8x B300.
Source: RadixArk · x.comPublished · added here