ToolsThe story, in brief
Google AI Edge Gallery launches on macOS, letting Mac users run Gemini models locally - 9to5Mac
Google just made running Gemini locally a reality. Gemma 4 12B analyzes audio and video on any 16GB laptop—no cloud required.
The KeyNews take
Why it matters
Google is shipping edge AI inference capabilities to developers and enterprises, enabling local agentic workflows without cloud dependency. This shifts the competitive landscape for on-device AI deployment and reduces latency/privacy concerns for real-time applications.
The key facts
6 to knowGemma 4 12B multimodal model (audio, video, text)
Runs on any laptop with 16GB RAM
Encoder-free architecture
Google AI Edge Gallery launched on macOS
Designed for local, agentic workflows
Open source
Go to the source
Reuters Technologynews.google.com
Publisher excerpt: Google AI Edge Gallery launches on macOS, letting Mac users run Gemini models locally 9to5Mac Introducing Gemma 4 12B: a unified, encoder-free multimodal model blog.google Bringing Gemma 4 12B to your Laptop: Unlocking Local, Agentic Workflows with Google AI Edge blog.google Google's new open…