Google's Gemma 4 12B brings encoder-free multimodal AI to laptops

Google DeepMind product managers Olivier Lacombe and Gus Martins announced Gemma 4 12B, a mid-sized open model under Apache 2.0 that runs multimodal and agentic tasks locally on laptops. The model bridges Google's edge-friendly E4B and its larger 26B Mixture of Experts system, delivering near-equivalent benchmark performance while using less than half the memory footprint.

Google DeepMind product managers Olivier Lacombe and Gus Martins introduced Gemma 4 12B, a mid sized open model designed to run multimodal and agentic workloads locally on laptops. https://www.youtube.com/watch?v=Q5a7dAREbXM Google says the Apache 2.0 model bridges its edge friendly E4B and its more advanced 26B Mixture of Experts model, offering benchmark performance near the larger system while using less than half the total memory footprint. The company says Google's Gemma 4 12B model can ...