Skip to main content
← Back to news

EmbeddingGemma 2: one space for text, images, video and audio, on consumer hardware

Model releases
Google DeepMind releases a 740M-parameter multimodal embedding model: text, code, images, video and audio in a unified 768-dimension space, 100+ languages, 8K context and Matryoshka vectors that cut storage by up to 6x. Apache 2.0, runs on phones and laptops.

Get the next local-AI briefing

Once a week, the top selection from iaLocale: articles, news and resources on local AI, and more.

After signing up you receive a confirmation email (double opt-in). Without confirmation we send nothing. No spam, we promise.