2 stories tagged #Multi-Token Prediction

  1. Google Launches Gemma 4 12B AI Model for Everyday Laptops
    tech

    Google Launches Gemma 4 12B AI Model for Everyday Laptops

    Google's new Gemma 4 12B runs on any laptop with 16GB of RAM, bringing powerful AI to local devices.

    2w ago 1 min read
  2. Google's Gemma 4 AI Models Get 3x Speed Boost by Predicting Future Tokens
    tech

    Google's Gemma 4 AI Models Get 3x Speed Boost by Predicting Future Tokens

    Google introduces Multi-Token Prediction for Gemma 4, speeding up local AI generation by up to 3x with speculative decoding.

    last mo. 1 min read