Model comparison

translategemma-12b-it vs Qwen3-8B

At Q4_K_M, Qwen3-8B is the smaller download — 5,027,783,488 bytes against 7,300,776,544.

From the file· summed bytes, KV per layer

Side by side

translategemma-12b-itQwen3-8B
Parameters13.2B8.2B
Architecturegemma3qwen3
Layers36
Native context40,960
Mixture of expertsnono
Quantizations published3651
Smallest quantization2.75 GiB2.12 GiB
Q4_K_M6.80 GiB4.68 GiB
Licencegemmaapache-2.0

KV cache by context

the term that decides long-context viability
Contexttranslategemma-12b-itQwen3-8BRatio
4,0960.56 GiB
8,1921.13 GiB
16,3842.25 GiB
32,7684.50 GiB
65,5369.00 GiB
131,07218.00 GiB