Is Qwen3.5-4B-heretic or Qwen3-VL-2B-Instruct smaller?

Qwen3-VL-2B-Instruct is smaller at Q4_K_M: 1.03 GiB against 2.52 GiB.

Which uses less memory at long context?

Qwen3.5-4B-heretic — its KV cache at 32K context is 3.5x smaller, because of how its attention layers cache.

Model comparison

Qwen3.5-4B-heretic vs Qwen3-VL-2B-Instruct

At Q4_K_M, Qwen3-VL-2B-Instruct is the smaller download — 1,107,409,952 bytes against 2,708,804,384. At long context the gap widens: Qwen3.5-4B-heretic's KV cache at 32K is 3.5× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.5-4B-heretic	Qwen3-VL-2B-Instruct
Parameters	4.5B	2.1B
Architecture	qwen35	qwen3vl
Layers	32	28
Native context	262,144	262,144
Mixture of experts	no	no
Quantizations published	6	46
Smallest quantization	0.64 GiB	0.50 GiB
Q4_K_M	2.52 GiB	1.03 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.5-4B-heretic	Qwen3-VL-2B-Instruct	Ratio
4,096	0.13 GiB	0.44 GiB	3.50×
8,192	0.25 GiB	0.88 GiB	3.50×
16,384	0.50 GiB	1.75 GiB	3.50×
32,768	1.00 GiB	3.50 GiB	3.50×
65,536	2.00 GiB	7.00 GiB	3.50×
131,072	4.00 GiB	14.00 GiB	3.50×