Is gemma-4-12B-it-qat-q4_0-unquantized or GLM-Z1-Rumination-32B-0414 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 3.1x smaller, because of how its attention layers cache.

Model comparison

gemma-4-12B-it-qat-q4_0-unquantized vs GLM-Z1-Rumination-32B-0414

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 3.1× 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	GLM-Z1-Rumination-32B-0414
Parameters	12.0B	33.1B
Architecture	gemma4	glm4
Layers	48	61
Native context	262,144	131,072
Mixture of experts	no	no
Quantizations published	2	29
Smallest quantization	6.50 GiB	9.45 GiB
Q4_K_M	—	18.66 GiB
Licence	apache-2.0	mit

KV cache by context

the term that decides long-context viability

Context	gemma-4-12B-it-qat-q4_0-unquantized	GLM-Z1-Rumination-32B-0414	Ratio
4,096	0.72 GiB	0.95 GiB	1.33×
8,192	0.97 GiB	1.91 GiB	1.97×
16,384	1.47 GiB	3.81 GiB	2.60×
32,768	2.47 GiB	7.63 GiB	3.09×
65,536	4.47 GiB	15.25 GiB	3.41×
131,072	8.47 GiB	30.50 GiB	3.60×