GoKawiilGoogle releases EmbeddingGemma 2 and debuts Foresight notetaking app for Mac
Google unveiled EmbeddingGemma 2, a 740-million-parameter multimodal AI model built on the Gemma 4 architecture and released under an Apache 2.0 license, designed to run locally on devices like Pixel phones using minimal RAM. The company also launched Google AI Edge Foresight, a Mac app that uses the model to transcribe meetings, expand shorthand notes into polished text, and answer questions by searching local files, calendars, and Google Drive content—all processed on-device.
GoKawiil's interpretation of the reporting above, not reported fact.
By emphasizing on-device processing, Google appears to be pitching EmbeddingGemma 2 as a privacy-friendly alternative to cloud-based AI assistants, which could appeal to users wary of sending meeting audio or personal files to remote servers. The compact size of the model suggests Google wants developers to build similar lightweight, local AI tools across phones and desktops, potentially expanding its AI ecosystem beyond cloud services.
- EmbeddingGemma 2 is a 740M-parameter multimodal model released under an Apache 2.0 open license.
- It can run with as little as ~191MB RAM for text-only tasks, enabling on-device use on phones like the Pixel 11 Pro.
- Google AI Edge Foresight is a new Mac app demonstrating the model's use for local, private meeting notetaking and file search.
Apple MacBook Air M2 — Since Google's new AI Edge Foresight notetaking app runs locally on Mac hardware, having a capable MacBook ensures smooth offline processing of audio and multimodal AI tasks. The MacBook Air's efficient chip is well-suited for running on-device AI models without draining battery life during long meetings.
See Apple MacBook Air M2 on Amazon → Affiliate link — we may earn a commission on purchases, at no extra cost to you. Product picked by AI based on this article; it is not a tested recommendation.Source: 9to5google.com — Abner Li, 2026-10-06
Published there as: “Google AI Edge Foresight for Mac turns scribbles into full notes using offline recordings”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.