Is LFM2-24B-A2B or gemma-4-E4B-it smaller?

gemma-4-E4B-it is smaller at Q4_K_M: 4.64 GiB against 13.43 GiB.

Which uses less memory at long context?

gemma-4-E4B-it — its KV cache at 32K context is 1.2x smaller, because of how its attention layers cache.

Model comparison

LFM2-24B-A2B vs gemma-4-E4B-it

At Q4_K_M, gemma-4-E4B-it is the smaller download — 4,977,171,584 bytes against 14,415,473,952. At long context the gap widens: gemma-4-E4B-it's KV cache at 32K is 1.2× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	LFM2-24B-A2B	gemma-4-E4B-it
Parameters	23.8B	8.0B
Architecture	lfm2moe	gemma4
Layers	40	42
Native context	128,000	131,072
Mixture of experts	yes, 64 experts	no
Quantizations published	33	36
Smallest quantization	5.35 GiB	3.30 GiB
Q4_K_M	13.43 GiB	4.64 GiB
Licence	other	apache-2.0

KV cache by context

the term that decides long-context viability

Context	LFM2-24B-A2B	gemma-4-E4B-it	Ratio
4,096	0.08 GiB	0.12 GiB	1.57×
8,192	0.16 GiB	0.18 GiB	1.14×
16,384	0.31 GiB	0.29 GiB	1.09×
32,768	0.63 GiB	0.51 GiB	1.24×
65,536	1.25 GiB	0.94 GiB	1.33×
131,072	2.50 GiB	1.82 GiB	1.37×