Is Qwen3-VL-8B-Thinking or Qwen3.5-4B smaller?

Qwen3.5-4B is smaller at Q4_K_M: 2.52 GiB against 4.68 GiB.

Which uses less memory at long context?

Qwen3.5-4B — its KV cache at 32K context is 4.5x smaller, because of how its attention layers cache.

Model comparison

Qwen3-VL-8B-Thinking vs Qwen3.5-4B

At Q4_K_M, Qwen3.5-4B is the smaller download — 2,707,513,696 bytes against 5,027,784,704. At long context the gap widens: Qwen3.5-4B's KV cache at 32K is 4.5× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3-VL-8B-Thinking	Qwen3.5-4B
Parameters	8.8B	4.7B
Architecture	qwen3vl	qwen35
Layers	36	32
Native context	262,144	262,144
Mixture of experts	no	no
Quantizations published	26	57
Smallest quantization	2.12 GiB	1.42 GiB
Q4_K_M	4.68 GiB	2.52 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3-VL-8B-Thinking	Qwen3.5-4B	Ratio
4,096	0.56 GiB	0.13 GiB	4.50×
8,192	1.13 GiB	0.25 GiB	4.50×
16,384	2.25 GiB	0.50 GiB	4.50×
32,768	4.50 GiB	1.00 GiB	4.50×
65,536	9.00 GiB	2.00 GiB	4.50×
131,072	18.00 GiB	4.00 GiB	4.50×