I read that the pre-training model behind Gemini 3 has 10T parameters. That does not mean that the model they’re serving each day has 10T parameters. The online model is likely distilled from 10T down to something smaller, but I have not had either fact confirmed by Google. These are anecdotes.
I read that the pre-training model behind Gemini 3 has 10T parameters. That does not mean that the model they’re serving each day has 10T parameters. The online model is likely distilled from 10T down to something smaller, but I have not had either fact confirmed by Google. These are anecdotes.