shipfeedAI news, curated daily

07:59:22 CET
24 JUN07:59:22shipfeed⋯
pull to refreshlast sync
Just in — 30 new
§ models · storyline

Google Deepmind's Gemma 4 12B squeezes multimodal AI onto a laptop with just 16 GB of RAM

Google DeepMind releases Gemma 4 12B, an open-source multimodal model handling text, images, and audio that runs on laptops with 16 GB of RAM under an Apache 2.0 licence.

Jun 3 · · primary fetch2 sourcesupdated Jun 3 ·

Google Deepmind's Gemma 4 12B is an open-source model that processes text, images, and audio natively and runs on laptops with just 16 GB of RAM. It nearly matches the twice-as-large 26B model in benchmarks and ships under an Apache 2.0 license for commercial use.

The article Google Deepmind's Gemma 4 12B squeezes multimodal AI onto a laptop with just 16 GB of RAM appeared first on The Decoder.

read full article on the-decoder.com ↗
§ sources2 publications · timeline below
  1. the-decoder.comGoogle Deepmind's Gemma 4 12B squeezes multimodal AI onto a laptop with just 16 GB of RAMprimary
  2. arstechnica.comGoogle's new Gemma 4 12B model is designed to run on any laptop with 16GB of RAM

§ how this story moved

  1. primary — Ars Technica — AI publishes the launch post.
  2. The Decoder picks up coverage.