Is ChatGPT-5 or Qwen3-4B smaller?

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

Which uses less memory at long context?

ChatGPT-5 — its KV cache at 32K context is 12.0x smaller, because of how its attention layers cache.

Model comparison

ChatGPT-5 vs Qwen3-4B

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: ChatGPT-5's KV cache at 32K is 12.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	ChatGPT-5	Qwen3-4B
Parameters	494M	4.0B
Architecture	qwen2	qwen3
Layers	24	36
Native context	32,768	40,960
Mixture of experts	no	no
Quantizations published	1	29
Smallest quantization	0.49 GiB	1.01 GiB
Q4_K_M	—	2.33 GiB
Licence	apache-2.0	—

KV cache by context

the term that decides long-context viability

Context	ChatGPT-5	Qwen3-4B	Ratio
4,096	0.05 GiB	0.56 GiB	12.00×
8,192	0.09 GiB	1.13 GiB	12.00×
16,384	0.19 GiB	2.25 GiB	12.00×
32,768	0.38 GiB	4.50 GiB	12.00×
65,536	0.75 GiB	9.00 GiB	12.00×
131,072	1.50 GiB	18.00 GiB	12.00×