Is gemma-4-12b-it-uncensored or gemma-4-E2B-it smaller?

gemma-4-E2B-it is smaller at Q4_K_M: 2.89 GiB against 6.87 GiB.

Which uses less memory at long context?

gemma-4-E2B-it — its KV cache at 32K context is 10.0x smaller, because of how its attention layers cache.

Model comparison

gemma-4-12b-it-uncensored vs gemma-4-E2B-it

At Q4_K_M, gemma-4-E2B-it is the smaller download — 3,106,738,272 bytes against 7,381,381,760. At long context the gap widens: gemma-4-E2B-it's KV cache at 32K is 10.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	gemma-4-12b-it-uncensored	gemma-4-E2B-it
Parameters	12.0B	5.1B
Architecture	gemma4	gemma4
Layers	48	35
Native context	131,072	131,072
Mixture of experts	no	no
Quantizations published	40	54
Smallest quantization	2.78 GiB	2.13 GiB
Q4_K_M	6.87 GiB	2.89 GiB
Licence	gemma	apache-2.0

KV cache by context

the term that decides long-context viability

Context	gemma-4-12b-it-uncensored	gemma-4-E2B-it	Ratio
4,096	0.72 GiB	0.05 GiB	13.14×
8,192	0.97 GiB	0.08 GiB	11.81×
16,384	1.47 GiB	0.14 GiB	10.74×
32,768	2.47 GiB	0.25 GiB	10.03×
65,536	4.47 GiB	0.46 GiB	9.61×
131,072	8.47 GiB	0.90 GiB	9.39×