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

1 · DeepMind · June 9, 2026, 2:39 p.m.
Machine Learning Multimodal Models DeepMind AI Models
Summary
DeepMind introduces Gemma 4 12B, a unified and encoder-free multimodal model that aims to advance interaction across various data types, although specifics on its uniqueness or potential applications are yet unpublished.
Read full post on deepmind.google →
AUTHOR