Google’s Gemma 4 AI models get 3x speed boost by predicting future tokens

The problem with rolling your own AI is that your system memory probably isn’t very fast compared to the high bandwidth ...
The Eastern Herald

Google Supercharges Gemma 4 With Multi-Token Prediction, Delivering Up to 3× Faster AI Inference

Google’s Multi-Token Prediction upgrade for Gemma 4 dramatically improves AI speed and efficiency without sacrificing ...
Decrypt

Google Found a Way to Make Local AI Up to 3x Faster—No New Hardware Required

Google's new Multi-Token Prediction drafters can make Gemma 4 run up to 3x faster on your own hardware—no cloud required, and ...
OfficeChai

Google Makes Gemma4 3x Faster Through Multi-Token Prediction Drafters

AI models aren’t only getting cheaper and more capable, but algorithmic advances are also helping them become faster. Google has released Multi-Token ...