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

Qwen3.5-2B is smaller at Q4_K_M: 1.18 GiB against 2.33 GiB.

Which uses less memory at long context?

Qwen3.5-2B — its KV cache at 32K context is 12.0x smaller, because of how its attention layers cache.

Model comparison

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

At Q4_K_M, Qwen3.5-2B is the smaller download — 1,270,808,032 bytes against 2,497,281,568. At long context the gap widens: Qwen3.5-2B's KV cache at 32K is 12.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3-VL-4B-Instruct	Qwen3.5-2B
Parameters	4.4B	2.3B
Architecture	qwen3vl	qwen35
Layers	36	24
Native context	262,144	262,144
Mixture of experts	no	no
Quantizations published	26	42
Smallest quantization	1.01 GiB	0.72 GiB
Q4_K_M	2.33 GiB	1.18 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3-VL-4B-Instruct	Qwen3.5-2B	Ratio
4,096	0.56 GiB	0.05 GiB	11.99×
8,192	1.13 GiB	0.09 GiB	12.00×
16,384	2.25 GiB	0.19 GiB	12.00×
32,768	4.50 GiB	0.38 GiB	12.00×
65,536	9.00 GiB	0.75 GiB	12.00×
131,072	18.00 GiB	1.50 GiB	12.00×