Is gemma-4-12B-it-qat-q4_0-unquantized or gemma-3-27b-it 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 1.3x smaller, because of how its attention layers cache.

Model comparison

gemma-4-12B-it-qat-q4_0-unquantized vs gemma-3-27b-it

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 1.3× 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-qat-q4_0-unquantized	gemma-3-27b-it
Parameters	12.0B	27.4B
Architecture	gemma4	gemma3
Layers	48	62
Native context	262,144	131,072
Mixture of experts	no	no
Quantizations published	2	48
Smallest quantization	6.50 GiB	6.06 GiB
Q4_K_M	—	15.41 GiB
Licence	apache-2.0	—

KV cache by context

the term that decides long-context viability

Context	gemma-4-12B-it-qat-q4_0-unquantized	gemma-3-27b-it	Ratio
4,096	0.72 GiB	0.92 GiB	1.28×
8,192	0.97 GiB	1.23 GiB	1.27×
16,384	1.47 GiB	1.86 GiB	1.27×
32,768	2.47 GiB	3.11 GiB	1.26×
65,536	4.47 GiB	5.61 GiB	1.26×
131,072	8.47 GiB	10.61 GiB	1.25×