Is gemma-3n-E2B-it or gemma-4-12B-it smaller?

gemma-3n-E2B-it is smaller at Q4_K_M: 2.60 GiB against 6.63 GiB.

Which uses less memory at long context?

gemma-3n-E2B-it — its KV cache at 32K context is 5.9x smaller, because of how its attention layers cache.

Model comparison

gemma-3n-E2B-it vs gemma-4-12B-it

At Q4_K_M, gemma-3n-E2B-it is the smaller download — 2,787,806,304 bytes against 7,121,861,440. At long context the gap widens: gemma-3n-E2B-it's KV cache at 32K is 5.9× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	gemma-3n-E2B-it	gemma-4-12B-it
Parameters	5.4B	12.0B
Architecture	gemma3n	gemma4
Layers	30	48
Native context	32,768	262,144
Mixture of experts	no	no
Quantizations published	40	59
Smallest quantization	1.76 GiB	3.92 GiB
Q4_K_M	2.60 GiB	6.63 GiB
Licence	gemma	apache-2.0

KV cache by context

the term that decides long-context viability

Context	gemma-3n-E2B-it	gemma-4-12B-it	Ratio
4,096	0.09 GiB	0.72 GiB	7.67×
8,192	0.14 GiB	0.97 GiB	6.89×
16,384	0.23 GiB	1.47 GiB	6.27×
32,768	0.42 GiB	2.47 GiB	5.85×
65,536	0.80 GiB	4.47 GiB	5.61×
131,072	1.55 GiB	8.47 GiB	5.47×