Is Qwen3-VL-32B-Instruct or Qwen3.6-35B-A3B smaller?

Qwen3-VL-32B-Instruct is smaller at Q4_K_M: 18.40 GiB against 19.71 GiB.

Which uses less memory at long context?

Qwen3.6-35B-A3B — its KV cache at 32K context is 12.8x smaller, because of how its attention layers cache.

Model comparison

Qwen3-VL-32B-Instruct vs Qwen3.6-35B-A3B

At Q4_K_M, Qwen3-VL-32B-Instruct is the smaller download — 19,762,150,432 bytes against 21,166,757,728. At long context the gap widens: Qwen3.6-35B-A3B's KV cache at 32K is 12.8× 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	Qwen3.6-35B-A3B
Parameters	33.4B	36.0B
Architecture	qwen3vl	qwen35moe
Layers	64	40
Native context	262,144	262,144
Mixture of experts	no	yes, 256 experts
Quantizations published	48	61
Smallest quantization	7.21 GiB	8.77 GiB
Q4_K_M	18.40 GiB	19.71 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3-VL-32B-Instruct	Qwen3.6-35B-A3B	Ratio
4,096	1.00 GiB	0.08 GiB	12.79×
8,192	2.00 GiB	0.16 GiB	12.80×
16,384	4.00 GiB	0.31 GiB	12.80×
32,768	8.00 GiB	0.63 GiB	12.80×
65,536	16.00 GiB	1.25 GiB	12.80×
131,072	32.00 GiB	2.50 GiB	12.80×