Is gemma-2-9b or gemma-4-12B-it-qat-q4_0-unquantized smaller?

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

Which uses less memory at long context?

gemma-4-12B-it-qat-q4_0-unquantized — its KV cache at 32K context is 2.4x smaller, because of how its attention layers cache.

Model comparison

gemma-2-9b vs gemma-4-12B-it-qat-q4_0-unquantized

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: gemma-4-12B-it-qat-q4_0-unquantized's KV cache at 32K is 2.4× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	gemma-2-9b	gemma-4-12B-it-qat-q4_0-unquantized
Parameters	9.2B	12.0B
Architecture	gemma2	gemma4
Layers	42	48
Native context	8,192	262,144
Mixture of experts	no	no
Quantizations published	18	2
Smallest quantization	3.54 GiB	6.50 GiB
Q4_K_M	5.37 GiB	—
Licence	gemma	apache-2.0

KV cache by context

the term that decides long-context viability

Context	gemma-2-9b	gemma-4-12B-it-qat-q4_0-unquantized	Ratio
4,096	1.31 GiB	0.72 GiB	1.83×
8,192	2.05 GiB	0.97 GiB	2.12×
16,384	3.36 GiB	1.47 GiB	2.29×
32,768	5.99 GiB	2.47 GiB	2.43×
65,536	11.24 GiB	4.47 GiB	2.51×
131,072	21.74 GiB	8.47 GiB	2.57×