Model comparison

Qwen3.5-2B-heretic vs Qwen3-VL-2B-Instruct

At Q4_K_M, Qwen3-VL-2B-Instruct is the smaller download — 1,107,409,952 bytes against 1,274,396,576. At long context the gap widens: Qwen3.5-2B-heretic's KV cache at 32K is 9.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

Qwen3.5-2B-hereticQwen3-VL-2B-Instruct
Parameters2.2B2.1B
Architectureclipqwen3vl
Layers2428
Native context262,144262,144
Mixture of expertsnono
Quantizations published646
Smallest quantization0.51 GiB0.50 GiB
Q4_K_M1.19 GiB1.03 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextQwen3.5-2B-hereticQwen3-VL-2B-InstructRatio
4,0960.05 GiB0.44 GiB9.33×
8,1920.09 GiB0.88 GiB9.33×
16,3840.19 GiB1.75 GiB9.33×
32,7680.38 GiB3.50 GiB9.33×
65,5360.75 GiB7.00 GiB9.33×
131,0721.50 GiB14.00 GiB9.33×
Qwen3.5-2B-heretic vs Qwen3-VL-2B-Instruct — size, memory and hardware fit — ossmodeldb