Model comparison

MiniCPM-V-4 vs Qwen3.5-4B

At Q4_K_M, MiniCPM-V-4 is the smaller download — 2,189,861,216 bytes against 2,707,513,696.

From the file· summed bytes, KV per layer

Side by side

MiniCPM-V-4Qwen3.5-4B
Parameters4.1B4.7B
Architecturellamaqwen35
Layers3232
Native context32,768262,144
Mixture of expertsnono
Quantizations published1057
Smallest quantization1.94 GiB1.42 GiB
Q4_K_M2.04 GiB2.52 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextMiniCPM-V-4Qwen3.5-4BRatio
4,0960.13 GiB0.13 GiB1.00×
8,1920.25 GiB0.25 GiB1.00×
16,3840.50 GiB0.50 GiB1.00×
32,7681.00 GiB1.00 GiB1.00×
65,5362.00 GiB2.00 GiB1.00×
131,0724.00 GiB4.00 GiB1.00×