Google's new Gemma 4 12B model is designed to run on any laptop with 16 GB of RAM

Google introduced Gemma 4, a 12‑billion‑parameter model optimized for laptops with 16 GB RAM. It employs a novel encoding scheme and token‑prediction technique that lets it perform competitively despite its modest size. The model aims to bring advanced LLM capabilities to consumer hardware.

Summary written by Kernelia from the original article by Ars Technica — AI. The story and its rights belong to its author.