Google releases EmbeddingGemma 2: open 270m-740m multimodal embeddings for on-device use
osanseviero · x · 2026-10-07
Google's team has unveiled EmbeddingGemma 2, a new open embeddings model (Apache 2.0) built for on-device use cases.
- Produces embeddings for code, image, video, audio, and text
- Modular, scaling from 270m to 740m parameters
- Uses Matryoshka embeddings for storage efficiency
Model weights and blog are now live, with the team praising how much capability was packed into the small size.
More from Models
- vLLM adds day-0 support for Google's multimodal EmbeddingGemma 2 — AccBalanced · 2026-10-07
- RedNote Has a Serious, Low-Key AI Lab, Argues Analyst Weighing Dots3 Results — teortaxesTex · 2026-10-07
- OpenAI Cuts API Rate Limit Tiers From Five to Three, Grow Tier Now at $500 — OpenAIDevs · 2026-10-07
- Users report GPT-6.1 Sol is slower and worse in practice, suspect sandbagging — rickasaurus · 2026-10-07
- 61–90% of AI-synthesized medical conclusions contain factual errors, SciConBench finds — manoelribeiro · 2026-10-07
- Cohere Labs Debuts Tiny Aya, a Small-Model Family Covering 70+ Languages — Cohere_Labs · 2026-10-07