Is Qwopus3.6-35B-A3B-v1 or Qwen3.5-9B smaller?

Qwen3.5-9B is smaller at Q4_K_M: 5.24 GiB against 20.22 GiB.

Which uses less memory at long context?

Qwopus3.6-35B-A3B-v1 — its KV cache at 32K context is 1.6x smaller, because of how its attention layers cache.

Model comparison

Qwopus3.6-35B-A3B-v1 vs Qwen3.5-9B

At Q4_K_M, Qwen3.5-9B is the smaller download — 5,627,044,256 bytes against 21,713,462,432. At long context the gap widens: Qwopus3.6-35B-A3B-v1's KV cache at 32K is 1.6× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwopus3.6-35B-A3B-v1	Qwen3.5-9B
Parameters	36.0B	9.7B
Architecture	clip	qwen35
Layers	40	32
Native context	262,144	262,144
Mixture of experts	yes, 256 experts	no
Quantizations published	29	34
Smallest quantization	6.97 GiB	2.97 GiB
Q4_K_M	20.22 GiB	5.24 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwopus3.6-35B-A3B-v1	Qwen3.5-9B	Ratio
4,096	0.08 GiB	0.13 GiB	1.60×
8,192	0.16 GiB	0.25 GiB	1.60×
16,384	0.31 GiB	0.50 GiB	1.60×
32,768	0.63 GiB	1.00 GiB	1.60×
65,536	1.25 GiB	2.00 GiB	1.60×
131,072	2.50 GiB	4.00 GiB	1.60×