local-inference-lab

/

GLM-5.3-Flash-NVFP4

like 30

Follow

local-inference-lab 32

Check the other quant, it fits fine

using https://github.com/local-inference-lab/vllm/tree/dev/jovian-judgement

https://huggingface.co/local-inference-lab/GLM-5.3-Flash-NVFP4-4p67

https://huggingface.co/local-inference-lab/GLM-5.3-Flash-NVFP4-4p67

Thank you I posted a comment on that other quant now. Can you please share the startup command and how much context we can get out of it please!