Model comparison

gemma-3-270m-it-qat-q4_0-unquantized vs Qwen3-0.6B

At Q4_K_M, gemma-3-270m-it-qat-q4_0-unquantized is the smaller download — 253,115,200 bytes against 396,705,472.

From the file· summed bytes, KV per layer

Side by side

gemma-3-270m-it-qat-q4_0-unquantizedQwen3-0.6B
Parameters268M752M
Architecturegemma3qwen3
Layers28
Native context40,960
Mixture of expertsnono
Quantizations published3944
Smallest quantization0.17 GiB0.20 GiB
Q4_K_M0.24 GiB0.37 GiB
Licencegemma

KV cache by context

the term that decides long-context viability
Contextgemma-3-270m-it-qat-q4_0-unquantizedQwen3-0.6BRatio
4,0960.44 GiB
8,1920.88 GiB
16,3841.75 GiB
32,7683.50 GiB
65,5367.00 GiB
131,07214.00 GiB