AI Foresights — A New Dawn Is Here
Back to homebest ai tools

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

Ars Technica AI May 6, 2026
Google's Gemma 4 AI models get 3x speed boost by predicting future tokens
AI Summary— plain English for professionals

# Google's AI Just Got Three Times Faster at One Specific Task Google has released a speed upgrade for its Gemma 4 AI models that makes them generate text much faster by predicting multiple words ahead of time, similar to how your phone's autocomplete guesses your next words. This is particularly useful if you want to run AI on your own computer instead of uploading everything to the cloud, since local hardware is typically slower than Google's powerful servers. The upgrade is free and available now for people who want to experiment with AI on their own devices.

Google launched its Gemma 4 open models this spring, promising a new level of power and performance for local AI. Google's take on edge AI could be getting even faster already with the release of Multi-Token Prediction (MTP) drafters for Gemma. Google says these experimental models leverage a form o

Read full article on Ars Technica AI

Get new guides every week

Real AI income strategies, tool reviews, and plain-English news — free in your inbox.

or enter email