Google DeepMind introduces Gemma 4, a family of state-of-the-art open models designed for on-device agentic workflows. Learn how to leverage multi-step planning, 140+ language support, and LiteRT-LM to build powerful, autonomous AI experiences across mobile, desktop, and IoT.

GoogleDevs' platform is a central hub for developers interested in Google technologies, APIs, and developer tools. Through articles, tutorials, and documentation, GoogleDevs offers insights into building applications using Google Cloud Platform, Android, Chrome, and other Google services. Developers can learn about cloud computing, machine learning, and mobile app development with Google's developer tools and platforms.

Google Developers

Google DeepMind has launched Gemma 4, a family of open models (Apache 2.0) designed for on-device agentic AI workflows. Key capabilities include multi-step planning, autonomous action, offline code generation, audio-visual processing, and support for 140+ languages — all without specialized fine-tuning. Developers can access Gemma 4 via Android's AICore Developer Preview or Google AI Edge. The new Agent Skills feature in Google AI Edge Gallery enables fully on-device autonomous workflows. LiteRT-LM, the underlying inference runtime, delivers strong performance: processing 4,000 tokens in under 3 seconds on mobile GPUs, and achieving 133 tokens/sec prefill on a Raspberry Pi 5. A new Python package and CLI tool (available on Linux, macOS, and Raspberry Pi) make it easy to experiment with Gemma 4 without writing code, including tool-calling support for agentic use cases.

Bring state-of-the-art agentic skills to the edge with Gemma 4

Leverage Gemma 4 across devices with LiteRT-LM