Is gemma-3-270m-it-qat or Qwen3-1.7B smaller?

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

Which uses less memory at long context?

gemma-3-270m-it-qat — its KV cache at 32K context is 32.3x smaller, because of how its attention layers cache.

Model comparison

gemma-3-270m-it-qat vs Qwen3-1.7B

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: gemma-3-270m-it-qat's KV cache at 32K is 32.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	gemma-3-270m-it-qat	Qwen3-1.7B
Parameters	268M	2.0B
Architecture	gemma3	qwen3
Layers	18	28
Native context	32,768	40,960
Mixture of experts	no	no
Quantizations published	1	48
Smallest quantization	0.22 GiB	0.50 GiB
Q4_K_M	—	1.03 GiB
Licence	—	—

KV cache by context

the term that decides long-context viability

Context	gemma-3-270m-it-qat	Qwen3-1.7B	Ratio
4,096	0.03 GiB	0.44 GiB	16.59×
8,192	0.04 GiB	0.88 GiB	22.97×
16,384	0.06 GiB	1.75 GiB	28.44×
32,768	0.11 GiB	3.50 GiB	32.29×
65,536	0.20 GiB	7.00 GiB	34.63×
131,072	0.39 GiB	14.00 GiB	35.93×