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

gemma-3-270m is smaller at Q4_K_M: 0.47 GiB against 1.03 GiB.

Which uses less memory at long context?

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

Model comparison

gemma-3-270m vs Qwen3-1.7B

At Q4_K_M, gemma-3-270m is the smaller download — 506,228,096 bytes against 1,107,409,472. At long context the gap widens: gemma-3-270m'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	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	30	48
Smallest quantization	0.22 GiB	0.50 GiB
Q4_K_M	0.47 GiB	1.03 GiB
Licence	gemma	—

KV cache by context

the term that decides long-context viability

Context	gemma-3-270m	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×