Is LFM2.5-8B-A1B or llama-3-youko-8b smaller?

Both publish quantizations; compare the table for the exact sizes.

Which uses less memory at long context?

LFM2.5-8B-A1B — its KV cache at 32K context is 10.7x smaller, because of how its attention layers cache.

Model comparison

LFM2.5-8B-A1B vs llama-3-youko-8b

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: LFM2.5-8B-A1B's KV cache at 32K is 10.7× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	LFM2.5-8B-A1B	llama-3-youko-8b
Parameters	8.5B	8.0B
Architecture	lfm2moe	llama
Layers	24	32
Native context	128,000	8,192
Mixture of experts	yes, 32 experts	no
Quantizations published	22	2
Smallest quantization	2.40 GiB	5.34 GiB
Q4_K_M	4.80 GiB	—
Licence	other	llama3

KV cache by context

the term that decides long-context viability

Context	LFM2.5-8B-A1B	llama-3-youko-8b	Ratio
4,096	0.05 GiB	0.50 GiB	10.66×
8,192	0.09 GiB	1.00 GiB	10.66×
16,384	0.19 GiB	2.00 GiB	10.66×
32,768	0.38 GiB	4.00 GiB	10.67×
65,536	0.75 GiB	8.00 GiB	10.67×
131,072	1.50 GiB	16.00 GiB	10.67×