Model comparison

gemma-4-12B-it-qat-q4_0-unquantized vs nsfwcaption-qwen3-vl-8b-v3-safetensors

These two publish different quantization sets; the table below has the exact sizes. At long context the gap widens: gemma-4-12B-it-qat-q4_0-unquantized's KV cache at 32K is 1.8× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

gemma-4-12B-it-qat-q4_0-unquantizednsfwcaption-qwen3-vl-8b-v3-safetensors
Parameters12.0B8.8B
Architecturegemma4qwen3vl
Layers4836
Native context262,144262,144
Mixture of expertsnono
Quantizations published212
Smallest quantization6.50 GiB3.06 GiB
Q4_K_M—4.68 GiB
Licenceapache-2.0—

KV cache by context

the term that decides long-context viability
Contextgemma-4-12B-it-qat-q4_0-unquantizednsfwcaption-qwen3-vl-8b-v3-safetensorsRatio
4,0960.72 GiB0.56 GiB1.28×
8,1920.97 GiB1.13 GiB1.16×
16,3841.47 GiB2.25 GiB1.53×
32,7682.47 GiB4.50 GiB1.82×
65,5364.47 GiB9.00 GiB2.01×
131,0728.47 GiB18.00 GiB2.13×