To gain a deeper understanding of the technical aspects of these capabilities and our approach to responsible development, please refer to the Gemma 3 technical report.

Implementing Rigorous Safety Protocols for Gemma 3 Development

We recognize that open models require meticulous risk assessment. Our approach balances innovation with safety by tailoring testing intensity to model capabilities. The development of Gemma 3 involved extensive data governance, alignment with our safety policies through fine-tuning, and robust benchmark evaluations. While thorough testing of more capable models often informs our assessment of less capable ones, Gemma 3’s enhanced STEM performance prompted specific evaluations focused on its potential for misuse in creating harmful substances, indicating a low risk level.

As the industry develops more powerful models, it will be crucial to collectively develop risk-proportionate approaches to safety. We will continue to learn and refine our safety practices for open models over time.

Enhanced Safety for Image Applications with ShieldGemma 2

Alongside Gemma 3, we are introducing ShieldGemma 2, a powerful 4B image safety checker built on the Gemma 3 foundation. ShieldGemma 2 provides a ready-made solution for image safety, outputting safety labels across three safety categories: dangerous content, sexually explicit, and violence. Developers can further customize ShieldGemma for their safety needs and users. ShieldGemma 2 is open and designed to give flexibility and control, leveraging the performance and efficiency of the Gemma 3 architecture to promote responsible AI development.

Seamless Integration with Existing Tools

Gemma 3 and ShieldGemma 2 integrate seamlessly into your existing workflows:

• Develop with your preferred tools: With support for Hugging Face Transformers, Ollama, JAX, Keras, PyTorch, Google AI Edge, UnSloth, vLLM, and Gemma.cpp, you have the flexibility to choose the best tools for your project.
• Start experimenting instantly: Get instant access to Gemma 3 and begin building right away. Explore its full potential in Google AI Studio or download the models through Kaggle or Hugging Face.
• Customize Gemma 3 to your specific needs: Gemma 3 ships with a revamped codebase that includes recipes for efficient fine-tuning and inference. Train and adapt the model using your preferred platform, like Google Colab, Vertex AI, or even your gaming GPU.
• Deploy your way: Gemma 3 offers multiple deployment options, including Vertex AI, Cloud Run, the Google GenAI API, local environments, and other platforms, giving you the flexibility to choose the best fit for your application and infrastructure.
• Experience optimized performance on NVIDIA GPUs: NVIDIA has directly optimized Gemma 3 models to ensure that you get maximum performance on GPUs of any size, from Jetson Nano to the latest Blackwell chips. Gemma 3 is now featured on the NVIDIA API Catalog, enabling rapid prototyping with just an API call.
• Accelerate your AI development across many hardware platforms: Gemma 3 is also optimized for Google Cloud TPUs and integrates with AMD GPUs via the open-source ROCm stack. For CPU execution, Gemma.cpp offers a direct solution.

The “Gemmaverse” Ecosystem of Models and Tools

The Gemmaverse is a vast ecosystem of community-created Gemma models and tools, ready to power and inspire your innovation. For example, AI Singapore’s SEA-LION v3 breaks down language barriers and fosters communication across Southeast Asia; INSAIT’s BgGPT is a pioneering Bulgarian-first large language model that demonstrates the power of Gemma to support diverse languages; and Nexa AI’s OmniAudio showcases the potential of on-device AI, bringing advanced audio processing capabilities to everyday devices.

To further promote academic research breakthroughs, we’re launching the Gemma 3 Academic Program. Academic researchers can apply for Google Cloud credits (worth $10,000 per award) to accelerate their Gemma 3-based research. The application form opens today and will remain open for four weeks. Apply on our website.

Getting Started with Gemma 3

As part of our ongoing commitment to democratizing access to high-quality AI, Gemma 3 represents the next step. Ready to explore Gemma 3? Here’s where to start:

Instant exploration:

• Try Gemma 3 at full precision directly in your browser – no setup needed – with Google AI Studio.
• Get an API key directly from Google AI Studio and use Gemma 3 with the Google GenAI SDK.

Customize and build:

• Download Gemma 3 models from Hugging Face, Ollama, or Kaggle.
• Easily fine-tune and adapt the model to your unique requirements with Hugging Face’s Transformers library or your preferred development environment.

Deploy and scale: