Model comparison

Qwen2-VL-2B-Instruct vs Qwen3-VL-2B-Instruct

At Q4_K_M, Qwen2-VL-2B-Instruct is the smaller download — 986,046,944 bytes against 1,107,409,952. At long context the gap widens: Qwen2-VL-2B-Instruct's KV cache at 32K is 4.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

Qwen2-VL-2B-InstructQwen3-VL-2B-Instruct
Parameters2.2B2.1B
Architectureqwen2vlqwen3vl
Layers2828
Native context32,768262,144
Mixture of expertsnono
Quantizations published2546
Smallest quantization0.56 GiB0.50 GiB
Q4_K_M0.92 GiB1.03 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen2-VL-2B-InstructQwen3-VL-2B-InstructRatio
4,0960.11 GiB0.44 GiB4.00×
8,1920.22 GiB0.88 GiB4.00×
16,3840.44 GiB1.75 GiB4.00×
32,7680.88 GiB3.50 GiB4.00×
65,5361.75 GiB7.00 GiB4.00×
131,0723.50 GiB14.00 GiB4.00×