Is Qwen3.5-88B or Qwen3-30B-A3B-Thinking-2507 smaller?

Qwen3-30B-A3B-Thinking-2507 is smaller at Q4_K_M: 17.28 GiB against 49.66 GiB.

Which uses less memory at long context?

Qwen3.5-88B — its KV cache at 32K context is 4.0x smaller, because of how its attention layers cache.

Model comparison

Qwen3.5-88B vs Qwen3-30B-A3B-Thinking-2507

At Q4_K_M, Qwen3-30B-A3B-Thinking-2507 is the smaller download — 18,556,685,824 bytes against 53,323,531,328. At long context the gap widens: Qwen3.5-88B's KV cache at 32K is 4.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.5-88B	Qwen3-30B-A3B-Thinking-2507
Parameters	87.7B	30.5B
Architecture	qwen35moe	qwen3moe
Layers	48	48
Native context	262,144	262,144
Mixture of experts	yes, 180 experts	yes, 128 experts
Quantizations published	33	51
Smallest quantization	17.20 GiB	7.05 GiB
Q4_K_M	49.66 GiB	17.28 GiB
Licence	other	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.5-88B	Qwen3-30B-A3B-Thinking-2507	Ratio
4,096	0.09 GiB	0.38 GiB	4.00×
8,192	0.19 GiB	0.75 GiB	4.00×
16,384	0.38 GiB	1.50 GiB	4.00×
32,768	0.75 GiB	3.00 GiB	4.00×
65,536	1.50 GiB	6.00 GiB	4.00×
131,072	3.00 GiB	12.00 GiB	4.00×