Is Qwen3-VL-30B-A3B-Thinking or Qwen3.6-35B-A3B smaller?

Qwen3-VL-30B-A3B-Thinking is smaller at Q4_K_M: 17.28 GiB against 19.71 GiB.

Which uses less memory at long context?

Qwen3.6-35B-A3B — its KV cache at 32K context is 4.8x smaller, because of how its attention layers cache.

Model comparison

Qwen3-VL-30B-A3B-Thinking vs Qwen3.6-35B-A3B

At Q4_K_M, Qwen3-VL-30B-A3B-Thinking is the smaller download — 18,556,687,200 bytes against 21,166,757,728. At long context the gap widens: Qwen3.6-35B-A3B's KV cache at 32K is 4.8× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3-VL-30B-A3B-Thinking	Qwen3.6-35B-A3B
Parameters	31.1B	36.0B
Architecture	qwen3vlmoe	qwen35moe
Layers	48	40
Native context	262,144	262,144
Mixture of experts	yes, 128 experts	yes, 256 experts
Quantizations published	49	61
Smallest quantization	7.05 GiB	8.77 GiB
Q4_K_M	17.28 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-30B-A3B-Thinking	Qwen3.6-35B-A3B	Ratio
4,096	0.38 GiB	0.08 GiB	4.80×
8,192	0.75 GiB	0.16 GiB	4.80×
16,384	1.50 GiB	0.31 GiB	4.80×
32,768	3.00 GiB	0.63 GiB	4.80×
65,536	6.00 GiB	1.25 GiB	4.80×
131,072	12.00 GiB	2.50 GiB	4.80×