Is gemma-3n-E4B-it or Qwen3.5-4B smaller?

Qwen3.5-4B is smaller at Q4_K_M: 2.52 GiB against 3.95 GiB.

Which uses less memory at long context?

gemma-3n-E4B-it — its KV cache at 32K context is 2.0x smaller, because of how its attention layers cache.

Model comparison

gemma-3n-E4B-it vs Qwen3.5-4B

At Q4_K_M, Qwen3.5-4B is the smaller download — 2,707,513,696 bytes against 4,237,064,064. At long context the gap widens: gemma-3n-E4B-it's KV cache at 32K is 2.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	gemma-3n-E4B-it	Qwen3.5-4B
Parameters	7.8B	4.7B
Architecture	gemma3n	qwen35
Layers	35	32
Native context	32,768	262,144
Mixture of experts	no	no
Quantizations published	38	57
Smallest quantization	2.57 GiB	1.42 GiB
Q4_K_M	3.95 GiB	2.52 GiB
Licence	gemma	apache-2.0

KV cache by context

the term that decides long-context viability

Context	gemma-3n-E4B-it	Qwen3.5-4B	Ratio
4,096	0.11 GiB	0.13 GiB	1.14×
8,192	0.16 GiB	0.25 GiB	1.52×
16,384	0.27 GiB	0.50 GiB	1.83×
32,768	0.49 GiB	1.00 GiB	2.03×
65,536	0.93 GiB	2.00 GiB	2.15×
131,072	1.80 GiB	4.00 GiB	2.22×