deployedbyai

The Deploy Log | Models and APIs

Gemma 4 12B

Gemma 4 12B is an encoder-free multimodal model that runs locally with 16GB of VRAM or unified memory, and Gemma 4 models have crossed 150 million downloads.

Google DeepMind | In Edition 38, Saturday 13 Jun 2026

SOURCE Google DeepMind, Introducing Gemma 4 12B: a unified, encoder-free multimodal model

Added to The Deploy Log Monday 14 Sep 2026, updated Thursday 17 Sep 2026. Read Edition 38, the edition that carried it.

The call on this one

What shipped is free. The call on it, what to do about it and the condition on that, opens with a signup: free, no card, every edition in full.

It becomes $50 a year, and signing up now keeps your first year free.