Is Qwen3-32B-qweh2 or gpt-oss-20b smaller?

Both publish quantizations; compare the table for the exact sizes.

Which uses less memory at long context?

gpt-oss-20b — its KV cache at 32K context is 10.4x smaller, because of how its attention layers cache.

Model comparison

Qwen3-32B-qweh2 vs gpt-oss-20b

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: gpt-oss-20b's KV cache at 32K is 10.4× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3-32B-qweh2	gpt-oss-20b
Parameters	32.8B	21.5B
Architecture	qwen3	gpt-oss
Layers	64	24
Native context	40,960	131,072
Mixture of experts	no	yes, 32 experts
Quantizations published	1	15
Smallest quantization	21.62 GiB	10.68 GiB
Q4_K_M	—	10.83 GiB
Licence	wtfpl	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3-32B-qweh2	gpt-oss-20b	Ratio
4,096	1.00 GiB	0.11 GiB	8.98×
8,192	2.00 GiB	0.21 GiB	9.75×
16,384	4.00 GiB	0.39 GiB	10.19×
32,768	8.00 GiB	0.77 GiB	10.42×
65,536	16.00 GiB	1.52 GiB	10.54×
131,072	32.00 GiB	3.02 GiB	10.60×