open ./04_compare.html

Same prompt, two models. Run Gemma 3 270M and Gemma 3 1B side by side and compare quality, speed, and token throughput.

setup load model files // both are optional — load whichever you have

Gemma 3 270M

Select .task file

Gemma 3 1B

Select .task file

Load whichever files you have selected — both aren't required.

prompt // ctrl+enter to generate

Gemma 3 270M

✓

q4 · fast but smaller

tokens: 0 time: 0.0s speed: —

Output will appear here…

Gemma 3 1B

✓

q8 · slower but smarter

tokens: 0 time: 0.0s speed: —

Output will appear here…