Model comparison

LFM2-VL-450M vs LFM2.5-VL-450M

At Q4_K_M, LFM2-VL-450M is the smaller download — 229,309,856 bytes against 229,313,568.

From the file· summed bytes, KV per layer

Side by side

LFM2-VL-450MLFM2.5-VL-450M
Parameters451M449M
Architecturelfm2lfm2
Layers1616
Native context128,000128,000
Mixture of expertsnono
Quantizations published309
Smallest quantization0.13 GiB0.20 GiB
Q4_K_M0.21 GiB0.21 GiB
Licenceotherother

KV cache by context

the term that decides long-context viability
ContextLFM2-VL-450MLFM2.5-VL-450MRatio
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×