Is gemma-3-1b-it or Qwen3-1.7B smaller?

gemma-3-1b-it is smaller at Q4_K_M: 0.75 GiB against 1.03 GiB.

Which uses less memory at long context?

gemma-3-1b-it — its KV cache at 32K context is 23.9x smaller, because of how its attention layers cache.

Model comparison

gemma-3-1b-it vs Qwen3-1.7B

At Q4_K_M, gemma-3-1b-it is the smaller download — 806,058,240 bytes against 1,107,409,472. At long context the gap widens: gemma-3-1b-it's KV cache at 32K is 23.9× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	gemma-3-1b-it	Qwen3-1.7B
Parameters	1000M	2.0B
Architecture	gemma3	qwen3
Layers	26	28
Native context	32,768	40,960
Mixture of experts	no	no
Quantizations published	28	48
Smallest quantization	0.52 GiB	0.50 GiB
Q4_K_M	0.75 GiB	1.03 GiB
Licence	gemma	—

KV cache by context

the term that decides long-context viability

Context	gemma-3-1b-it	Qwen3-1.7B	Ratio
4,096	0.04 GiB	0.44 GiB	11.79×
8,192	0.05 GiB	0.88 GiB	16.59×
16,384	0.08 GiB	1.75 GiB	20.84×
32,768	0.15 GiB	3.50 GiB	23.89×
65,536	0.27 GiB	7.00 GiB	25.78×
131,072	0.52 GiB	14.00 GiB	26.85×