Model comparison

rfdetr vs tinygemma3_cifar

These two publish different quantization sets; the table below has the exact sizes.

From the file· summed bytes, KV per layer

Side by side

rfdetrtinygemma3_cifar
Parameters30M39M
Architecturerfdetrgemma3
Layers8
Native context131,072
Mixture of expertsnono
Quantizations published121
Smallest quantization0.03 GiB0.04 GiB
Q4_K_M
Licenceapache-2.0wtfpl

KV cache by context

the term that decides long-context viability
Contextrfdetrtinygemma3_cifarRatio
4,0960.06 GiB
8,1920.08 GiB
16,3840.09 GiB
32,7680.12 GiB
65,5360.19 GiB
131,0720.31 GiB