Is Qwen3-VL-32B-Instruct or Qwen3.5-9B smaller?

Qwen3.5-9B is smaller at Q4_K_M: 5.24 GiB against 18.40 GiB.

Which uses less memory at long context?

Qwen3.5-9B — its KV cache at 32K context is 8.0x smaller, because of how its attention layers cache.

Model comparison

Qwen3-VL-32B-Instruct vs Qwen3.5-9B

At Q4_K_M, Qwen3.5-9B is the smaller download — 5,627,044,256 bytes against 19,762,150,432. At long context the gap widens: Qwen3.5-9B's KV cache at 32K is 8.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3-VL-32B-Instruct	Qwen3.5-9B
Parameters	33.4B	9.7B
Architecture	qwen3vl	qwen35
Layers	64	32
Native context	262,144	262,144
Mixture of experts	no	no
Quantizations published	48	34
Smallest quantization	7.21 GiB	2.97 GiB
Q4_K_M	18.40 GiB	5.24 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3-VL-32B-Instruct	Qwen3.5-9B	Ratio
4,096	1.00 GiB	0.13 GiB	7.99×
8,192	2.00 GiB	0.25 GiB	8.00×
16,384	4.00 GiB	0.50 GiB	8.00×
32,768	8.00 GiB	1.00 GiB	8.00×
65,536	16.00 GiB	2.00 GiB	8.00×
131,072	32.00 GiB	4.00 GiB	8.00×