Is gemma-4-12B-it-qat-q4_0-unquantized or Qwopus3.6-27B-v2-abliterated smaller?

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

Which uses less memory at long context?

Qwopus3.6-27B-v2-abliterated — its KV cache at 32K context is 1.2x smaller, because of how its attention layers cache.

Model comparison

gemma-4-12B-it-qat-q4_0-unquantized vs Qwopus3.6-27B-v2-abliterated

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: Qwopus3.6-27B-v2-abliterated's KV cache at 32K is 1.2× 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	Qwopus3.6-27B-v2-abliterated
Parameters	12.0B	27.4B
Architecture	gemma4	qwen35
Layers	48	64
Native context	262,144	262,144
Mixture of experts	no	no
Quantizations published	2	30
Smallest quantization	6.50 GiB	10.12 GiB
Q4_K_M	—	15.66 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	Qwopus3.6-27B-v2-abliterated	Ratio
4,096	0.72 GiB	0.25 GiB	2.87×
8,192	0.97 GiB	0.50 GiB	1.94×
16,384	1.47 GiB	1.00 GiB	1.47×
32,768	2.47 GiB	2.00 GiB	1.23×
65,536	4.47 GiB	4.00 GiB	1.12×
131,072	8.47 GiB	8.00 GiB	1.06×