Model comparison

Qwen3-VL-2B-Instruct vs Qwen3-VL-4B-Instruct

At Q4_K_M, Qwen3-VL-2B-Instruct is the smaller download — 1,107,409,952 bytes against 2,497,281,568. At long context the gap widens: Qwen3-VL-2B-Instruct's KV cache at 32K is 1.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

Qwen3-VL-2B-InstructQwen3-VL-4B-Instruct
Parameters2.1B4.4B
Architectureqwen3vlqwen3vl
Layers2836
Native context262,144262,144
Mixture of expertsnono
Quantizations published4626
Smallest quantization0.50 GiB1.01 GiB
Q4_K_M1.03 GiB2.33 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3-VL-2B-InstructQwen3-VL-4B-InstructRatio
4,0960.44 GiB0.56 GiB1.29×
8,1920.88 GiB1.13 GiB1.29×
16,3841.75 GiB2.25 GiB1.29×
32,7683.50 GiB4.50 GiB1.29×
65,5367.00 GiB9.00 GiB1.29×
131,07214.00 GiB18.00 GiB1.29×
Qwen3-VL-2B-Instruct vs Qwen3-VL-4B-Instruct — size, memory and hardware fit — ossmodeldb