Is Qwen3-VL-8B-Thinking or gemma-4-E2B-it smaller?

gemma-4-E2B-it is smaller at Q4_K_M: 2.89 GiB against 4.68 GiB.

Which uses less memory at long context?

gemma-4-E2B-it — its KV cache at 32K context is 18.3x smaller, because of how its attention layers cache.

Model comparison

Qwen3-VL-8B-Thinking vs gemma-4-E2B-it

At Q4_K_M, gemma-4-E2B-it is the smaller download — 3,106,738,272 bytes against 5,027,784,704. At long context the gap widens: gemma-4-E2B-it's KV cache at 32K is 18.3× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3-VL-8B-Thinking	gemma-4-E2B-it
Parameters	8.8B	5.1B
Architecture	qwen3vl	gemma4
Layers	36	35
Native context	262,144	131,072
Mixture of experts	no	no
Quantizations published	26	54
Smallest quantization	2.12 GiB	2.13 GiB
Q4_K_M	4.68 GiB	2.89 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3-VL-8B-Thinking	gemma-4-E2B-it	Ratio
4,096	0.56 GiB	0.05 GiB	10.29×
8,192	1.13 GiB	0.08 GiB	13.71×
16,384	2.25 GiB	0.14 GiB	16.46×
32,768	4.50 GiB	0.25 GiB	18.29×
65,536	9.00 GiB	0.46 GiB	19.36×
131,072	18.00 GiB	0.90 GiB	19.95×