October 6, 2026 · The Decoder
Google releases EmbeddingGemma 2, a 740M open multimodal embedding model
EmbeddingGemma 2 has 740 million parameters and converts text, images, video, audio and code into vectors. It needs about 191 MB of RAM, runs on-device, and Google says it outperforms some models twice its size. MarkTechPost reports it is built on Gemma 4 and ships under Apache 2.0.
Why it matters: A small, permissively licensed multimodal embedder makes fully offline retrieval-augmented generation (RAG) practical when paired with a small open model like Gemma 4. It fits the broader push toward private, on-device AI, and removes a common reason apps send data to external APIs.
Related updates
- ByteDance's open Axion 1.0 agent rivals top models with three training phasesNov 21
- OpenAI ships GPT-Live-1.1 voice model and cuts idle billingNov 21
- Thinking Machines releases open Inkling 2 Mini, a looped model for laptopsNov 21
- Anthropic mathematician claims Riemann hypothesis proof with Claude's helpNov 20