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

LFM2-350M-Extract 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 3.5x smaller, because of how its attention layers cache.

Model comparison

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

At Q4_K_M, LFM2-350M-Extract is the smaller download — 229,310,080 bytes against 253,115,168. At long context the gap widens: gemma-3-270m-it's KV cache at 32K is 3.5× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	LFM2-350M-Extract	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	29	39
Smallest quantization	0.13 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-Extract	gemma-3-270m-it	Ratio
4,096	0.05 GiB	0.03 GiB	1.78×
8,192	0.09 GiB	0.04 GiB	2.46×
16,384	0.19 GiB	0.06 GiB	3.05×
32,768	0.38 GiB	0.11 GiB	3.46×
65,536	0.75 GiB	0.20 GiB	3.71×
131,072	1.50 GiB	0.39 GiB	3.85×