Tracked topic
Gemma is a family of open-weight language models released by Google for text generation and related NLP tasks.
The process uses a technique called “Speculative Decoding,” in which the drafter models predict upcoming words in the prompt even before the main Gemma model has read through it. While the drafter moves on to the next sequence of words, the main model verifies the predicted set of words at the same time.
Google's latest trick gets Gemma 4 running 3x faster right on your phone… By • April 9, 2026 • • • Add AndroidAuthority on Google Google TL;DR Google’s AI Edge Gallery app is now officially available on the Google Play Store and Apple App Store. The app allows users to run the brand-new Gemma 4 model entirely on-device, requiring no internet connection. …
… By • May 6, 2026 • • • Add AndroidAuthority on Google Google TL;DR Google has introduced new assistant models, called “drafters,” that could significantly speed up Gemma 4. …
… By • April 11, 2026 • • • Add AndroidAuthority on Google Earlier this month, Google lifted the lid on its latest and most powerful Gemma 4 AI models that you can run on your own hardware. …
