Is glm4.1v-9b-base-sft or gemma-4-E4B-it smaller?

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

Which uses less memory at long context?

gemma-4-E4B-it — its KV cache at 32K context is 2.5x smaller, because of how its attention layers cache.

Model comparison

glm4.1v-9b-base-sft vs gemma-4-E4B-it

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: gemma-4-E4B-it's KV cache at 32K is 2.5× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	glm4.1v-9b-base-sft	gemma-4-E4B-it
Parameters	10.3B	8.0B
Architecture	glm4	gemma4
Layers	40	42
Native context	65,536	131,072
Mixture of experts	no	no
Quantizations published	24	36
Smallest quantization	2.90 GiB	3.30 GiB
Q4_K_M	—	4.64 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	glm4.1v-9b-base-sft	gemma-4-E4B-it	Ratio
4,096	0.16 GiB	0.12 GiB	1.27×
8,192	0.31 GiB	0.18 GiB	1.76×
16,384	0.63 GiB	0.29 GiB	2.18×
32,768	1.25 GiB	0.51 GiB	2.47×
65,536	2.50 GiB	0.94 GiB	2.65×
131,072	5.00 GiB	1.82 GiB	2.75×