Is gemma-3-4b-it-qat or gemma-4-E4B-it smaller?

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

Which uses less memory at long context?

gemma-4-E4B-it — its KV cache at 32K context is 1.6x smaller, because of how its attention layers cache.

Model comparison

gemma-3-4b-it-qat vs gemma-4-E4B-it

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: gemma-4-E4B-it's KV cache at 32K is 1.6× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	gemma-3-4b-it-qat	gemma-4-E4B-it
Parameters	3.9B	8.0B
Architecture	gemma3	gemma4
Layers	34	42
Native context	131,072	131,072
Mixture of experts	no	no
Quantizations published	1	36
Smallest quantization	2.35 GiB	3.30 GiB
Q4_K_M	—	4.64 GiB
Licence	—	apache-2.0

KV cache by context

the term that decides long-context viability

Context	gemma-3-4b-it-qat	gemma-4-E4B-it	Ratio
4,096	0.25 GiB	0.12 GiB	2.02×
8,192	0.33 GiB	0.18 GiB	1.84×
16,384	0.48 GiB	0.29 GiB	1.68×
32,768	0.79 GiB	0.51 GiB	1.57×
65,536	1.42 GiB	0.94 GiB	1.51×
131,072	2.67 GiB	1.82 GiB	1.47×