Model comparison

MiniCPM-V-4.6 vs Qwen3.5-2B

At Q4_K_M, MiniCPM-V-4.6 is the smaller download — 529,101,504 bytes against 1,270,808,032.

From the file· summed bytes, KV per layer

Side by side

MiniCPM-V-4.6Qwen3.5-2B
Parameters1.3B2.3B
Architectureqwen35qwen35
Layers2424
Native context262,144262,144
Mixture of expertsnono
Quantizations published1542
Smallest quantization0.47 GiB0.72 GiB
Q4_K_M0.49 GiB1.18 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextMiniCPM-V-4.6Qwen3.5-2BRatio
4,0960.05 GiB0.05 GiB1.00×
8,1920.09 GiB0.09 GiB1.00×
16,3840.19 GiB0.19 GiB1.00×
32,7680.38 GiB0.38 GiB1.00×
65,5360.75 GiB0.75 GiB1.00×
131,0721.50 GiB1.50 GiB1.00×