Model comparison

OvisOCR2 vs LFM2.5-VL-1.6B

At Q4_K_M, OvisOCR2 is the smaller download — 529,297,280 bytes against 730,895,968.

From the file· summed bytes, KV per layer

Side by side

OvisOCR2LFM2.5-VL-1.6B
Parameters853M1.6B
Architectureqwen35lfm2
Layers2416
Native context262,144128,000
Mixture of expertsnono
Quantizations published4323
Smallest quantization0.35 GiB0.45 GiB
Q4_K_M0.49 GiB0.68 GiB
Licenceapache-2.0other

KV cache by context

the term that decides long-context viability
ContextOvisOCR2LFM2.5-VL-1.6BRatio
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×