Model comparison

gemma-4-12B-it vs MiniCPM-V-4_5

At Q4_K_M, MiniCPM-V-4_5 is the smaller download — 5,026,714,560 bytes against 7,121,861,440. At long context the gap widens: gemma-4-12B-it's KV cache at 32K is 1.8× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

gemma-4-12B-itMiniCPM-V-4_5
Parameters12.0B8.7B
Architecturegemma4qwen3
Layers4836
Native context262,14440,960
Mixture of expertsnono
Quantizations published5928
Smallest quantization3.92 GiB3.06 GiB
Q4_K_M6.63 GiB4.68 GiB
Licenceapache-2.0—

KV cache by context

the term that decides long-context viability
Contextgemma-4-12B-itMiniCPM-V-4_5Ratio
4,0960.72 GiB0.56 GiB1.28×
8,1920.97 GiB1.13 GiB1.16×
16,3841.47 GiB2.25 GiB1.53×
32,7682.47 GiB4.50 GiB1.82×
65,5364.47 GiB9.00 GiB2.01×
131,0728.47 GiB18.00 GiB2.13×
gemma-4-12B-it vs MiniCPM-V-4_5 — size, memory and hardware fit — ossmodeldb