Developers · Updated 15 Oct, 04:17 pm IST
Google’s Antigravity SDK adds local model support with Gemma 4 26B
Why it matters for readers: It lets you try advanced AI agents without constantly sending data to cloud servers, useful for privacy and offline use.
- Antigravity SDK now supports local execution across a range of local models and execution options.1
- Initial support includes Gemma 4 26B A4B using Google AI Edge’s LiteRT runtime (LiteRT).1
- Google says the workflow is optimized for LiteRT and Gemma 4 26B to efficiently use local GPU and RAM.1
- Google lists advantages of running agents locally: cost efficiency, privacy, offline resiliency and hybrid cloud/local workflows.1
- Google recommends machines with more than 24 GB of VRAM or unified memory and provides a Python virtual environment setup to get started.1
Get a brief like this every morning
Uzha reads hundreds of sources and gives you the stories that matter for your work, with every source linked. Free.
Get started