Gemma 4 Tech Report: Open-Source Native Multimodal Models

burkov · x · 2026-07-08

Google released the Gemma 4 technical report, introducing a new generation of open-source, natively multimodal language models. The Gemma 4 series features both dense and Mixture-of-Experts (MoE) architectures, with parameter sizes ranging from 2.3B to 31B, aiming to boost computational efficiency and reasoning capabilities.

All model sizes feature improved vision and audio encoders. Notably, the 12B model adopts a unified encoder-free architecture, allowing it to process raw audio and image patches directly. Additionally, it integrates a thinking mode, enabling the model to generate a chain of thought before answering.

Related event: Google Releases Gemma 4 Technical Report Detailing Native Multimodal Architecture(10 posts)→

Original post →

More from Models

Models channel →