Get Started

Bring multimodal semantic search to the edge with EmbeddingGemma 2

LaunchML Frameworks & TrainingComputer Vision

First reported · 3h ago · 1 source

Crest summary — written by AI from the 1 source below; every figure is checked against them · model deepseek-flash

Summary

Google released EmbeddingGemma 2, a 740M open-weight multimodal model that maps text, images and video for semantic search on edge devices.

Key facts

  • EmbeddingGemma 2 is an open-weight model with 740M parameters.
  • The model handles text, images and video.
  • Google announced it on 2026-10-24.

Why it matters

Developers can run multimodal semantic search on edge hardware using open weights, rather than depending on a hosted service.

Companies

Technologies

  • EmbeddingGemma 2model

Original sources (1)

The report this event was built from. Crest of Tech keeps no article bodies: the full text is at each source.

  1. Google Developers BlogOfficial · Primary
    Bring multimodal semantic search to the edge with EmbeddingGemma 2Publish time not given
    Read at Google Developers Blog
Bring multimodal semantic search to the edge with EmbeddingGemma 2 — Crest of Tech