Is GLM-4-32B-0414 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?

GLM-4-32B-0414 — its KV cache at 32K context is 1.3x smaller, because of how its attention layers cache.

Model comparison

GLM-4-32B-0414 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: GLM-4-32B-0414'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

	GLM-4-32B-0414	gemma-4-12B-it-qat-q4_0-unquantized
Parameters	32.6B	12.0B
Architecture	glm4	gemma4
Layers	61	48
Native context	32,768	262,144
Mixture of experts	no	no
Quantizations published	49	2
Smallest quantization	7.17 GiB	6.50 GiB
Q4_K_M	18.33 GiB	—
Licence	mit	apache-2.0

KV cache by context

the term that decides long-context viability

Context	GLM-4-32B-0414	gemma-4-12B-it-qat-q4_0-unquantized	Ratio
4,096	0.24 GiB	0.72 GiB	3.02×
8,192	0.48 GiB	0.97 GiB	2.03×
16,384	0.95 GiB	1.47 GiB	1.54×
32,768	1.91 GiB	2.47 GiB	1.30×
65,536	3.81 GiB	4.47 GiB	1.17×
131,072	7.63 GiB	8.47 GiB	1.11×