modelsJun 9
Introducing Gemma 4 12B: a unified, encoder-free multimodal model
Google DeepMind introduced Gemma 4 12B, a unified multimodal model that processes text, images, and audio without separate encoders. The model is designed to handle complex, multi-modal tasks in a single architecture. You can explore Gemma 4 12B's capabilities on the DeepMind website. This development may interest builders working on multi-modal applications.
Key takeaways
- Unified architecture for text, images, and audio.
- No separate encoders for different modalities.
- Available for exploration on DeepMind website.