Bringing advanced agentic capabilities to the edge with Gemma 4
Original title:Bring state-of-the-art agentic skills to the edge with Gemma 4
AI summary
Google DeepMind released the open-source Gemma 4 series, designed to enable multi-step planning and autonomous agent workflows directly on devices. The release includes Google AI Edge Gallery for experimenting with agent skills, as well as the LiteRT-LM library, which provides developers with significant speed improvements and structured output. Gemma 4 is released under the Apache 2.0 license, supports more than 140 languages, and is compatible with a variety of IoT hardware platforms including mobile devices, desktops, and Raspberry Pi.
Key Takeaways
- Google DeepMind released the open-source Gemma 4 series,designed to enable multi-step planning and…
- The release includes Google AI Edge Gallery for experimenting with agent skills,as well as the…
- Gemma 4 is released under the Apache 2.
- 0 license,supports more than 140 languages,and is compatible with a variety of IoT hardware…
Quick Facts
- Published
- Updated
- Source
- Google Developers Blog(RSS)
- Category
- Other
- AI score
- 81
开源 agentic 模型支持端侧运行,开发者可快速构建本地智能应用。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Bringing advanced agentic capabilities to the edge with Gemma 4. April 2, 2026. https://new.nat6.net/en/news/cmoegbhpz00hmslxxode0j01e/