Is gemma-4-12B-it-qat-q4_0-unquantized or glm-4-9b-chat 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 8.1x smaller, because of how its attention layers cache.

Model comparison

gemma-4-12B-it-qat-q4_0-unquantized vs glm-4-9b-chat

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 8.1× 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-4-9b-chat
Parameters	12.0B	9.4B
Architecture	gemma4	chatglm
Layers	48	40
Native context	262,144	—
Mixture of experts	no	no
Quantizations published	2	58
Smallest quantization	6.50 GiB	2.89 GiB
Q4_K_M	—	5.82 GiB
Licence	apache-2.0	other

KV cache by context

the term that decides long-context viability

Context	gemma-4-12B-it-qat-q4_0-unquantized	glm-4-9b-chat	Ratio
4,096	0.72 GiB	2.50 GiB	3.48×
8,192	0.97 GiB	5.00 GiB	5.16×
16,384	1.47 GiB	10.00 GiB	6.81×
32,768	2.47 GiB	20.00 GiB	8.10×
65,536	4.47 GiB	40.00 GiB	8.95×
131,072	8.47 GiB	80.00 GiB	9.45×