Google introduces Gemma 4 model, purpose-built for advanced reasoning and agentic workflows; Gemma 4 now available in Android Studio, Google AI Studio and more

Yesterday, Google officially released its Gemma 4 model, that delivers an unprecedented level of intelligence-per-parameter.

We just released Gemma 4 — our most intelligent open models to date.

Built from the same world-class research as Gemini 3, Gemma 4 brings breakthrough intelligence directly to your own hardware for advanced reasoning and agentic workflows.

Released under a commercially… pic.twitter.com/W6Tvj9CuHW

— Google (@Google) April 2, 2026

Gemma 4

Built from the same world-class research and technology as Gemini 3. Gemma 4 is the most capable model family you can run on your hardware.

Gemma 4 is released in four versatile sizes: Effective 2B (E2B), Effective 4B (E4B), 26B Mixture of Experts (MoE) and 31B Dense. 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. Meanwhile, the E2B and E4B models redefine on-device utility, prioritizing multimodal capabilities, low-latency processing and seamless ecosystem integration over raw parameter count.

Features that make Gemma 4 the most capable open model family yet:

• Advanced reasoning- Gemma 4 demonstrates significant improvements in math and instruction-following benchmarks that require it.
• Agentic workflows- Native support for function-calling, structured JSON output, and native system instructions enables you to build autonomous agents that can interact with different tools and APIs and execute workflows 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 excelling at visual tasks like OCR and chart understanding. Additionally, the E2B and E4B models feature native audio input for speech recognition and understanding.
• Longer context- Process long-form content seamlessly. The edge models feature a 128K context window, while the larger models offer up to 256K.
• 140+ languages- Natively trained on over 140 languages.

The 26B and 31B models are frontier intelligence for personal computers, while the E2B and E4B models are a new level of intelligence for mobile and IoT devices.

Gemma 4 is released under a commercially permissive Apache 2.0 license that provides a foundation for complete developer flexibility and digital sovereignty.

Availability

Gemma 4 is available in Google AI Studio (31B or 26B MoE) or in Google AI Edge Gallery (E4B and E2B). For Android development, use it to power Agent Mode in Android Studio, and start building apps for production on Android with the ML Kit GenAI Prompt API.

Gemma 4 comes with day-one support for Hugging Face (Transformers, TRL, Transformers.js, Candle), LiteRT-LM, vLLM, llama.cpp, MLX, Ollama, NVIDIA NIM and NeMo, LM Studio, Unsloth, SGLang, Cactus, Baseten, Docker, MaxText, Tunix, and Keras.

Users can train and adapt the Gemma 4 model using their preferred platform, like Google Colab, Vertex AI or even your gaming GPU. Gemma 4 is optimized for industry-leading hardware out of the box. Experience maximum performance on NVIDIA AI infrastructure from NVIDIA Jetson Orin Nano to Blackwell GPUs, integrate with AMD GPUs via the open-source ROCm stack, or deploy on Trillium and Ironwood TPUs for massive scale and efficiency.

Gemma 4 available in Android Studio

By running locally on your machine, Gemma 4 gives you AI code assistance that doesn’t require an internet connection or an API key for its core operations. Key benefits include- Privacy and security, cost efficiency, offline availability and state-of-the-art reasoning.

Gemma 4 is now available in Android Studio!

By running Gemma 4 locally on your machine you get access to AI code-assistance that doesn't require an internet connection or an API key for its core operations — so you’ll never run out of token quota → https://t.co/1XFsPIDP6P pic.twitter.com/lsplY4s8UR

— Android Studio (@AndroidStudio) April 2, 2026

Gemma 4 was trained for Android development with agentic tool calling capabilities. When you select Gemma 4 as your local model, you can leverage Agent Mode for a variety of development use cases like- designing new features, refactoring, bug fixing and build resolution.

Recommended hardware requirements:

• Gemma E2B- 8GB total RAM needed, 2GB storage
• Gemma E4B- 12GB RAM, 4GB storage
• Gemma 26B MoE- 24GB RAM, 17GB storage

To get started

• Install the latest version of Android studio
• Install an LLM provider, such as LM Studio or Ollama, on your local computer
• In Settings> Tools> AI> Model Providers add your LM Studio or Ollama instance
• Download the Gemma 4 model from Ollama or LM Studio
• In Agent mode, select Gemma 4 as your active model