Is gemma-4-12B-it-qat-q4_0-unquantized or granite-4.0-h-small smaller?

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

Which uses less memory at long context?

granite-4.0-h-small — its KV cache at 32K context is 4.9x smaller, because of how its attention layers cache.

Model comparison

gemma-4-12B-it-qat-q4_0-unquantized vs granite-4.0-h-small

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: granite-4.0-h-small's KV cache at 32K is 4.9× 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	granite-4.0-h-small
Parameters	12.0B	32.2B
Architecture	gemma4	granitehybrid
Layers	48	40
Native context	262,144	131,072
Mixture of experts	no	yes, 72 experts
Quantizations published	2	41
Smallest quantization	6.50 GiB	7.59 GiB
Q4_K_M	—	18.14 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	granite-4.0-h-small	Ratio
4,096	0.72 GiB	0.06 GiB	11.47×
8,192	0.97 GiB	0.13 GiB	7.74×
16,384	1.47 GiB	0.25 GiB	5.87×
32,768	2.47 GiB	0.50 GiB	4.94×
65,536	4.47 GiB	1.00 GiB	4.47×
131,072	8.47 GiB	2.00 GiB	4.23×