Is GLM-4.1V-9B-Thinking or gemma-4-E2B-it smaller?

gemma-4-E2B-it is smaller at Q4_K_M: 2.89 GiB against 5.74 GiB.

Which uses less memory at long context?

gemma-4-E2B-it — its KV cache at 32K context is 5.1x smaller, because of how its attention layers cache.

Model comparison

GLM-4.1V-9B-Thinking vs gemma-4-E2B-it

At Q4_K_M, gemma-4-E2B-it is the smaller download — 3,106,738,272 bytes against 6,166,574,432. At long context the gap widens: gemma-4-E2B-it's KV cache at 32K is 5.1× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	GLM-4.1V-9B-Thinking	gemma-4-E2B-it
Parameters	10.3B	5.1B
Architecture	glm4	gemma4
Layers	40	35
Native context	65,536	131,072
Mixture of experts	no	no
Quantizations published	43	54
Smallest quantization	2.98 GiB	2.13 GiB
Q4_K_M	5.74 GiB	2.89 GiB
Licence	mit	apache-2.0

KV cache by context

the term that decides long-context viability

Context	GLM-4.1V-9B-Thinking	gemma-4-E2B-it	Ratio
4,096	0.16 GiB	0.05 GiB	2.86×
8,192	0.31 GiB	0.08 GiB	3.81×
16,384	0.63 GiB	0.14 GiB	4.57×
32,768	1.25 GiB	0.25 GiB	5.08×
65,536	2.50 GiB	0.46 GiB	5.38×
131,072	5.00 GiB	0.90 GiB	5.54×