Model comparison

LFM2.5-350M vs LFM2.5-1.2B-Instruct

At Q4_K_M, LFM2.5-350M is the smaller download — 228,332,128 bytes against 730,895,168.

From the file· summed bytes, KV per layer

Side by side

LFM2.5-350MLFM2.5-1.2B-Instruct
Parameters354M1.2B
Architecturelfm2lfm2
Layers1616
Native context128,000128,000
Mixture of expertsnono
Quantizations published1323
Smallest quantization0.20 GiB0.45 GiB
Q4_K_M0.21 GiB0.68 GiB
Licenceotherother

KV cache by context

the term that decides long-context viability
ContextLFM2.5-350MLFM2.5-1.2B-InstructRatio
4,0960.05 GiB0.05 GiB1.00×
8,1920.09 GiB0.09 GiB1.00×
16,3840.19 GiB0.19 GiB1.00×
32,7680.38 GiB0.38 GiB1.00×
65,5360.75 GiB0.75 GiB1.00×
131,0721.50 GiB1.50 GiB1.00×