Model comparison

MiMo-V2.5-Pro 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

MiMo-V2.5-ProGLM-5.2
Parameters1023B753B
Architecturemimo2glm-dsa
Layers7078
Native context1,048,5761,048,576
Mixture of expertsyes, 384 expertsyes, 256 experts
Quantizations published4020
Smallest quantization197.49 GiB169.33 GiB
Q4_K_M580.09 GiB
Licencemitmit

KV cache by context

the term that decides long-context viability
ContextMiMo-V2.5-ProGLM-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