Model comparison

gpt2 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

gpt2tinygemma3_cifar
Parameters137M39M
Architecturegpt2gemma3
Layers128
Native context131,072
Mixture of expertsnono
Quantizations published491
Smallest quantization0.06 GiB0.04 GiB
Q4_K_M0.11 GiB
Licencewtfpl

KV cache by context

the term that decides long-context viability
Contextgpt2tinygemma3_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