TLDRocket
Sign in

Google releases EmbeddingGemma 2, an open Apache 2.0 multimodal embedding model for on-device cross-modal search

Model release ● Confirmed 85% confidence first seen

Google released EmbeddingGemma 2, an open (Apache 2.0) multimodal embedding model that maps text, images, audio, and video into a shared embedding space for on-device use. The coverage describes support for building offline cross-modal search and retrieval with reduced memory/storage requirements, including deployment options such as quantization and truncating vector dimensions without retraining.

EmbeddingGemma 2 Google Google DeepMind Android ML Kit Apache 2.0 Apache 2.0 license GPT-4 Hacker News LiteRT MediaPipe Tasks OpenAI Pixel 11 Pro

Source coverage

Your phone’s vector index might be bigger than the AI model running it The New Stack EmbeddingGemma 2: an open, lightweight multimodal embedding model Google official EmbeddingGemma 2 Simon Willison’s Weblog industry analysis

The daily briefing

Every AI story that matters, in your inbox by 8am.

TLDRocket reads all relevant sources, removes duplicate coverage, and summarises the day in two minutes. Follow companies and topics for alerts, or get the briefing in Slack. Free, no spam, unsubscribe anytime.