Model comparison

GLM-5.2-FP8-Uncensored vs GLM-5.2

These two publish different quantization sets; the table below has the exact sizes.

From the file· summed bytes, KV per layer

Side by side

GLM-5.2-FP8-UncensoredGLM-5.2
Parameters753B753B
Architectureglm-dsaglm-dsa
Layers78
Native context1,048,576
Mixture of expertsnoyes, 256 experts
Quantizations published720
Smallest quantization276.94 GiB169.33 GiB
Q4_K_M423.33 GiB
Licencemitmit

KV cache by context

the term that decides long-context viability
ContextGLM-5.2-FP8-UncensoredGLM-5.2Ratio
4,0960.34 GiB
8,1920.69 GiB
16,3841.37 GiB
32,7682.74 GiB
65,5365.48 GiB
131,07210.97 GiB