6 stories
Google has introduced support for local models in the Antigravity SDK, enabling developers to build and execute agentic workflows directly on their own machines, while retaining the flexibility to mix in cloud-based models for higher-level tasks.
Google’s new AI Edge Foresight app takes on Granola with an offline meeting note-taker that can transcribe conversations, generate notes, and answer questions using on-device AI.
My comment on EmbeddingGemma 2 — Hacker News.I really appreciate that EmbeddingGemma 2 is under the Apache 2.0 license. For embedding models in particular, I don't think it makes sense to use a closed, proprietary, hosted-only model.
Google released EmbeddingGemma 2, an open model with 740 million parameters that converts text, images, video, audio, and code into vectors. It runs on-device, needs only about 191 MB of RAM, and outperforms some competing models twice its size, according to Google.
Ask the starred-repo corpus questions in natural language: embed the query on-device, rank the stored vectors, and show the matching repos in the TanStack Start UI. This is where the earlier chapters pay off.
In this video, we will learn how to install Google's open-source Gemma 4 model on an HP OmniBook 5, and use it without the internet. I will drop six months of credit card statements into it and it will give me comp; It read the whole thing and returned a categorised expense breakdown.
Showing 6 of 6 stories
You're all caught up.
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
