Model comparison

MiMo-V2.5 vs DeepSeek-V4-Flash

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-V2.5DeepSeek-V4-Flash
Parameters311B291B
Architecturemimo2deepseek4
Layers4843
Native context1,048,5761,048,576
Mixture of expertsyes, 256 expertsyes, 256 experts
Quantizations published4412
Smallest quantization60.09 GiB76.87 GiB
Q4_K_M175.80 GiB
Licencemitmit

KV cache by context

the term that decides long-context viability
ContextMiMo-V2.5DeepSeek-V4-FlashRatio
4,0960.06 GiB
8,1920.06 GiB
16,3840.06 GiB
32,7680.06 GiB
65,5360.06 GiB
131,0720.06 GiB