Google's EmbeddingGemma 2 (740M) claims to beat embedding rivals twice its size
The Decoder · rss · 2026-10-07
Google released EmbeddingGemma 2, an open embedding model with 740 million parameters that converts text, images, video, audio and code into vectors. Google claims it outperforms some rivals twice its size while running on-device with only about 191 MB of RAM. Paired with a small open model like Gemma 4, it enables fully offline RAG apps without sending data to external servers.
More from Models
- Western labs less likely to distill from Claude but more likely from GLM 5.3 — andrew_n_carr · 2026-10-07
- With OpenAI's Luna, cloud beats open weights on price — at least GPUs heat the house — BLUECOW009 · 2026-10-07
- V4.1 Flash review: top of Flash tier but wild hallucination swings, tester wary of V4.1 Pro — teortaxesTex · 2026-10-07
- OpenAI Launches Decisions API in Public Beta, Up to 10x Faster Than GPT-6 Luna — stevenheidel · 2026-10-07
- OpenAI to watermark ChatGPT outputs by default in the EU under AI Act — Ars Technica AI · 2026-10-07
- Mistral trained ML4 on 3,800 Grace Blackwell GPUs in its European datacenter, more clusters coming — rakyll · 2026-10-07