Kimi k3 is natively mxfp4 w/ mxfp8 activations. Since they talk about glm 5.2 running on a 8x b200s, that's likely fp8 since it wouldn't fit at bf16 (1.5TB weights alone)
Kimi k3 is natively mxfp4 w/ mxfp8 activations. Since they talk about glm 5.2 running on a 8x b200s, that's likely fp8 since it wouldn't fit at bf16 (1.5TB weights alone)
HuggingFace used an NVFP4 quant of GLM-5.2 to investigate their latest hack, so that might also be worth a try:
https://huggingface.co/nvidia/GLM-5.2-NVFP4