Google DeepMind has launched Gemma 4, a family of state-of-the-art open models designed to enable multi-step planning and autonomous agentic workflows directly on-device. The release includes the Google AI Edge Gallery for experimenting with “Agent Skills” and the LiteRT-LM library, which offers a significant speed boost and structured output for developers. Available under an Apache 2.0 license, Gemma 4 supports over 140 languages and is compatible with a wide range of hardware, including mobile devices, desktops, and IoT platforms like Raspberry Pi.
Bring state-of-the-art agentic skills to the edge with Gemma 4
Related Posts
Deploy Next.js Supabase App to Cloud Run using Artifact Registry and Secrets Manager
Table of Contents Introduction Step 1: Set Up Your Google Cloud Project Create a Google Cloud Project Install…
Learn Web Development by Building Projects
In the first episode of AskDevs twitter spaces, I spoke with self-taught developers on the relevance of coding…
Build Your Own Food Tracker with OpenAI Platform
The Benefits of Food Tracking Whether your goal is to lose weight, gain muscle, or simply maintain a…
