ai/ machine-learning · google · gemma

Google launches Gemma 4 12B model that fits on 16 GB laptops

The 12‑billion‑parameter Gemma 4 model, released June 3, runs on a typical laptop with 16 GB RAM using a new encoding scheme.

  • Google unveiled Gemma 4 12B on June 3, 2026.

The model packs 12 billion parameters yet can operate on any laptop that has 16 GB of RAM. Google achieves this by switching to a novel encoding scheme and a token‑prediction strategy that reduces memory overhead. The model is distributed as a downloadable package, but the exact file size was not disclosed.

This matters because earlier Gemma releases required desktop‑class hardware or cloud resources to run. By shrinking the memory footprint, Gemma 4 makes local LLM experimentation more accessible to developers who only have a standard notebook.

The move echoes a broader push to democratise AI execution, though performance will still lag behind larger, server‑grade models.

TR

The Revision

Written by an AI system from the public sources credited above. How we write →