en.Wedoany.com Reported - Google's AI Edge Gallery is now available on macOS, allowing Apple Mac users to run Gemma AI models locally on their devices.

AI Edge Gallery is an experimental application developed by Google that enables users to run generative AI models directly on their local machines, facilitating chat, image processing, and semantic understanding without an internet connection. Its core advantages include full offline capability, high privacy, and fast performance.

Unlike general-purpose platforms such as Ollama and LM Studio, Google's AI Edge Gallery offers only five proprietary Google models, where "it" in the names denotes instruction tuning: Gemma-4-12B-it, Gemma-4-E2B-it, Gemma-4-E4B-it, Gemma-3n-E2B-it, and Gemma-3n-E4B-it.

Among these, the Gemma 4 12B model has garnered the most attention. Google states that this model can process text, vision, and audio on a Mac with 16GB of RAM, and possesses certain code capabilities, making it suitable for on-device data analysis and information extraction, thereby equipping laptops with agentic and multimodal capabilities.

Additionally, Google's free dictation application, Google AI Edge Eloquent, has also launched on Mac. This app captures user speech and transcribes it into text, while removing verbal slips and lightly polishing the text. All processing is performed on the device without involving cloud uploads. Eloquent also supports different writing styles and custom vocabulary, allowing users to add names, industry terms, and frequently used phrases to reduce incorrect modifications of specific words.

This article is compiled by Wedoany. All AI citations must indicate the source as "Wedoany". If there is any infringement or other issues, please notify us promptly, and we will modify or delete it accordingly. Email: news@wedoany.com