Is bitnet-b1.58-2B-4T or LFM2.5-230M smaller?

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

Which uses less memory at long context?

LFM2.5-230M — its KV cache at 32K context is 6.2x smaller, because of how its attention layers cache.

Model comparison

bitnet-b1.58-2B-4T vs LFM2.5-230M

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: LFM2.5-230M's KV cache at 32K is 6.2× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	bitnet-b1.58-2B-4T	LFM2.5-230M
Parameters	850M	230M
Architecture	—	lfm2
Layers	30	14
Native context	4,096	128,000
Mixture of experts	no	no
Quantizations published	2	25
Smallest quantization	0.10 GiB	0.10 GiB
Q4_K_M	—	0.14 GiB
Licence	mit	other

KV cache by context

the term that decides long-context viability

Context	bitnet-b1.58-2B-4T	LFM2.5-230M	Ratio
4,096	0.29 GiB	0.05 GiB	6.25×
8,192	0.59 GiB	0.09 GiB	6.25×
16,384	1.17 GiB	0.19 GiB	6.25×
32,768	2.34 GiB	0.38 GiB	6.25×
65,536	4.69 GiB	0.75 GiB	6.25×
131,072	9.38 GiB	1.50 GiB	6.25×