Is LFM2-350M or gemma-3-270m-it smaller?

LFM2-350M is smaller at Q4_K_M: 0.21 GiB against 0.24 GiB.

Which uses less memory at long context?

gemma-3-270m-it — its KV cache at 32K context is 9.2x smaller, because of how its attention layers cache.

Model comparison

LFM2-350M vs gemma-3-270m-it

At Q4_K_M, LFM2-350M is the smaller download — 229,309,152 bytes against 253,115,168. At long context the gap widens: gemma-3-270m-it's KV cache at 32K is 9.2× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	LFM2-350M	gemma-3-270m-it
Parameters	354M	268M
Architecture	lfm2	gemma3
Layers	16	18
Native context	128,000	32,768
Mixture of experts	no	no
Quantizations published	19	39
Smallest quantization	0.15 GiB	0.17 GiB
Q4_K_M	0.21 GiB	0.24 GiB
Licence	other	gemma

KV cache by context

the term that decides long-context viability

Context	LFM2-350M	gemma-3-270m-it	Ratio
4,096	0.13 GiB	0.03 GiB	4.74×
8,192	0.25 GiB	0.04 GiB	6.56×
16,384	0.50 GiB	0.06 GiB	8.13×
32,768	1.00 GiB	0.11 GiB	9.23×
65,536	2.00 GiB	0.20 GiB	9.89×
131,072	4.00 GiB	0.39 GiB	10.27×