Today, we introduce Gemma 4 — our most intelligent open models to date. Purpose-built for advanced reasoning and agentic workflows, Gemma 4 delivers an unprecedented level of intelligence-per-parameter. This breakthrough builds on incredible community momentum: since the launch of our first generation, developers have downloaded Gemma over 400 million times, creating a vibrant Gemmaverse of more than 100,000 variants. We listened closely to what innovators need next to push the boundaries of AI, and Gemma 4 is our answer: breakthrough capabilities made widely accessible under an Apache 2.0 license.
The Gemma 4 family is released in four versatile sizes: Effective 2B (E2B), Effective 4B (E4B), 26B Mixture of Experts (MoE), and 31B Dense. The entire family moves beyond simple chat to handle complex logic and agentic workflows. Our larger models deliver state-of-the-art performance for their sizes, with the 31B model currently ranking as the #3 open model in the world on the industry-standard Arena AI text leaderboard, and the 26B model securing the #6 spot. Here, Gemma 4 outcompetes models 20x its size.
For developers, this new level of intelligence-per-parameter means achieving frontier-level capabilities with significantly less hardware overhead. At the edge, our E2B and E4B models redefine on-device utility, prioritizing multimodal capabilities, low-latency processing, and seamless ecosystem integration over raw parameter count.
Designed to run and fine-tune efficiently on hardware, Gemma 4 models can be utilized from billions of Android devices worldwide to laptop GPUs, and all the way up to developer workstations and accelerators. By using these highly optimized models, you can fine-tune Gemma 4 to achieve state-of-the-art performance on your specific tasks.
Here’s what makes Gemma 4 our most capable open model family yet:
- Advanced reasoning: Capable of multi-step planning and deep logic, Gemma 4 shows significant improvements in math and instruction-following benchmarks.
- Agentic workflows: Native support for function-calling, structured JSON output, and native system instructions enables building autonomous agents that can interact with different tools and APIs reliably.
- Code generation: Gemma 4 supports high-quality offline code, turning your workstation into a local-first AI code assistant.
- Vision and audio: All models natively process video and images, supporting variable resolutions, and excel at visual tasks like OCR and chart understanding.
- Longer context: Seamlessly process long-form content. Edge models feature a 128K context window, while larger models offer up to 256K, allowing you to pass repositories or long documents in a single prompt.
- 140+ languages: Natively trained on over 140 languages, Gemma 4 helps developers build inclusive, high-performance applications for a global audience.
Gemma 4's model weights are released in sizes tailored for specific hardware and use cases, ensuring frontier-class reasoning wherever you need it. The open-source license empowers developers with complete flexibility and digital sovereignty, allowing secure deployments across any environment.
Choosing Gemma 4, enterprises and sovereign organizations gain a trusted foundation that delivers state-of-the-art capabilities while meeting the highest standards for security and reliability. Start experimenting in seconds: Get instant access to Gemma 4 and begin building right away. Explore Gemma 4 in Google AI Studio, or in Google AI Edge Gallery. Android developers can use it to power Agent Mode in Android Studio and start building production apps for Android.
Blogger's Review: The release of Gemma 4 marks a significant advancement in open-source AI models, with its capabilities in multimodal processing and efficient reasoning set to enhance developers' innovative potential. The open Apache 2.0 license lowers entry barriers and encourages broader applications and ecosystem development. Its flexibility and powerful hardware compatibility will play a crucial role in future implementations.