Google launches EmbeddingGemma 2, a 740M open multimodal embedding model for on-device use
sundarpichai · x · 2026-10-07
Google has released EmbeddingGemma 2, its first open, natively multimodal embedding model, announced by Sundar Pichai.
- Just 740M parameters, unifying text, code, image, video, and audio in a shared embedding space
- Designed for on-device, offline, privacy-first RAG (pairs well with Gemma models)
- Outperforms some specialist models more than twice its size
Weights are available now on Hugging Face.
Related event: Google releases open-source multimodal EmbeddingGemma 2(27 posts)→
More from Infra
- 21M model + 6.4B SSD-resident lookup table matches a 114M dense model — fechyyy · 2026-10-07
- Ollama 0.35 adds local decision models from Cloudflare, Together and Bespoke — Technovangelist · 2026-10-07
- CostGraph becomes a drop-in InfraCost replacement for comparing GPU prices from L40 to A100 — saheedniyi_02 · 2026-10-07
- Oki Home launches a $1,799 Memory Computer running a 27B model locally with up to 16TB Memchip storage — Scobleizer · 2026-10-07
- AveniatsHub runs Qwen3 and Gemma3 fully offline on Android — MiraMooreIloveLLM · 2026-10-07
- Phonon-2 hits 606x real-time on a MacBook Air: one hour of speech in 6 seconds — julianweisser · 2026-10-07