Day-one estimate
Calculated from an estimated parameter count — the maker hasn't published one. Every model on this site is calculated the
same way, so the comparison holds even where the absolute value carries uncertainty.
Our figures are good to roughly a factor of two to three, which is why we only ever
state a difference of 5× or more.
The figure above is an understatement. Gemma 4 31B IT generates reasoning text you never see, and that text costs energy to produce. Our calculation counts a fixed answer length, so the real figure is higher — we cannot say by how much, because the amount is not published.
Is there a better choice?
A lighter model that does the job
Nothing we track is both at least as capable as Gemma 4 31B IT and meaningfully lighter. On our figures this is already a sensible choice for its standard of work.
What Google DeepMind publishes
Energy cannot be worked out without knowing how big a model is. Of the 20 models
from Google DeepMind that we track, 13 can be assessed at all — the rest publish
too little for anyone outside the company to calculate anything.