Is Qwen3.5-2B-Base or gemma-4-E2B-it smaller?

Qwen3.5-2B-Base is smaller at Q4_K_M: 1.19 GiB against 2.89 GiB.

Which uses less memory at long context?

gemma-4-E2B-it — its KV cache at 32K context is 1.5x smaller, because of how its attention layers cache.

Model comparison

Qwen3.5-2B-Base vs gemma-4-E2B-it

At Q4_K_M, Qwen3.5-2B-Base is the smaller download — 1,274,396,032 bytes against 3,106,738,272. At long context the gap widens: gemma-4-E2B-it's KV cache at 32K is 1.5× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.5-2B-Base	gemma-4-E2B-it
Parameters	2.3B	5.1B
Architecture	qwen35	gemma4
Layers	24	35
Native context	262,144	131,072
Mixture of experts	no	no
Quantizations published	8	54
Smallest quantization	1.15 GiB	2.13 GiB
Q4_K_M	1.19 GiB	2.89 GiB
Licence	apache-2.0	apache-2.0

KV cache by context

the term that decides long-context viability

Context	Qwen3.5-2B-Base	gemma-4-E2B-it	Ratio
4,096	0.05 GiB	0.05 GiB	1.17×
8,192	0.09 GiB	0.08 GiB	1.14×
16,384	0.19 GiB	0.14 GiB	1.37×
32,768	0.38 GiB	0.25 GiB	1.52×
65,536	0.75 GiB	0.46 GiB	1.61×
131,072	1.50 GiB	0.90 GiB	1.66×