Is gemma-3-27b-it-abliterated-refined-vision 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 1.3x smaller, because of how its attention layers cache.

Model comparison

gemma-3-27b-it-abliterated-refined-vision 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 1.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	gemma-3-27b-it-abliterated-refined-vision	gemma-4-12B-it-qat-q4_0-unquantized
Parameters	27.4B	12.0B
Architecture	gemma3	gemma4
Layers	62	48
Native context	131,072	262,144
Mixture of experts	no	no
Quantizations published	34	2
Smallest quantization	5.83 GiB	6.50 GiB
Q4_K_M	15.41 GiB	—
Licence	gemma	apache-2.0

KV cache by context

the term that decides long-context viability

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