Is LocateAnything-3B or gemma-4-E2B-it smaller?

LocateAnything-3B is smaller at Q4_K_M: 1.96 GiB against 2.89 GiB.

Which uses less memory at long context?

gemma-4-E2B-it — its KV cache at 32K context is 4.6x smaller, because of how its attention layers cache.

Model comparison

LocateAnything-3B vs gemma-4-E2B-it

At Q4_K_M, LocateAnything-3B is the smaller download — 2,107,054,176 bytes against 3,106,738,272. At long context the gap widens: gemma-4-E2B-it's KV cache at 32K is 4.6× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	LocateAnything-3B	gemma-4-E2B-it
Parameters	3.8B	5.1B
Architecture	qwen2	gemma4
Layers	36	35
Native context	32,768	131,072
Mixture of experts	no	no
Quantizations published	17	54
Smallest quantization	1.28 GiB	2.13 GiB
Q4_K_M	1.96 GiB	2.89 GiB
Licence	other	apache-2.0

KV cache by context

the term that decides long-context viability

Context	LocateAnything-3B	gemma-4-E2B-it	Ratio
4,096	0.14 GiB	0.05 GiB	2.57×
8,192	0.28 GiB	0.08 GiB	3.43×
16,384	0.56 GiB	0.14 GiB	4.11×
32,768	1.13 GiB	0.25 GiB	4.57×
65,536	2.25 GiB	0.46 GiB	4.84×
131,072	4.50 GiB	0.90 GiB	4.99×