Unveiling Gemma 3: The Most Powerful Model Operable on a Single GPU or TPU

Here’s a revised version with external references replaced:

For a deeper dive into the technical details behind these capabilities, as well as a comprehensive overview of our approach to responsible development, refer to the Gemma 3 technical report.

Rigorous Safety Protocols to Build Gemma 3 Responsibly
We believe open models require careful risk assessment, and our approach balances innovation with safety—tailoring testing intensity to model capabilities. Gemma 3’s development included extensive data governance, alignment with our safety policies via 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; the results indicate a low risk level. As the industry develops more powerful models, it will be critical to collaboratively develop risk-proportionate approaches to safety. We will continue to learn and refine our safety practices for open models over time.

Built-in Safety for Image Applications with ShieldGemma 2
Alongside Gemma 3, we’re also launching 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 categories: dangerous content, sexually explicit material, and violence. Developers can further customize ShieldGemma for their safety needs and users, offering flexibility and control while leveraging the performance and efficiency of the Gemma 3 architecture to promote responsible AI development.

Ready to Integrate with Your Existing Tools
Gemma 3 and ShieldGemma 2 integrate seamlessly into your workflows:

• Develop with your favorite 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 easily: Gain access to Gemma 3 and begin building right away. Explore its full potential in Google AI Studio and download the models through various platforms.

• Customize Gemma 3 to your specific needs: Gemma 3 ships with a revamped codebase that includes recipes for efficient fine-tuning and inference. Adapt the model using your preferred platform, such as Google Colab or Vertex AI.

• Deploy your way: Gemma 3 offers multiple deployment options including Vertex AI, Cloud Run, the Google GenAI API, local environments, and other platforms, allowing you to choose the best fit for your application and infrastructure.

• Experience optimized performance on NVIDIA GPUs: Gemma 3 models are optimized to ensure maximum performance on GPUs of any size. Gemma 3 is now featured on the NVIDIA API Catalog, enabling rapid prototyping with just an API call.

• Accelerate your AI development across various hardware: 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.

A “Gemmaverse” of Models and Tools
The Gemmaverse is a vast ecosystem of community-created Gemma models and tools, ready to inspire your innovation. For example, community projects break down language barriers, foster communication across diverse regions, and showcase the potential of on-device AI.

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.

Get Started with Gemma 3
As part of our ongoing commitment to democratizing access to high-quality AI, Gemma 3 represents the next step. 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 from Google AI Studio and use Gemma 3 with the Google GenAI SDK.

• Customize and build: Download Gemma 3 models and easily fine-tune and adapt the model to your unique requirements with our offerings and your preferred development environment.

• Deploy and scale:

Let me know if you need any more changes!