Google open-sources EmbeddingGemma 2: offline multimodal RAG on phones in ~567MB RAM
Saboo_Shubham_ · x · 2026-10-07
Google released EmbeddingGemma 2, an open-weights embedding model enabling fully offline multimodal RAG on phones: 191MB RAM for text search, 567MB for text + image + video + audio, measured on a Pixel 11 Pro. Weights are released under Apache 2.0.
More from Models
- "Astra Pause Syndrome": steering may be making models go silent, OpenAI has a workaround — thursdai_pod · 2026-10-07
- Unverified rumor suggests Qwen4 Flash is a 400B parameter model, comparable to GLM 5.3 Flash — EAccelerate_42 · 2026-10-07
- Anthropic Expands Cyber Verification Program With Three Tiers, Opens Door to Authorized Offensive Work — EricBuess · 2026-10-07
- Mistral Large 4.0 weights reportedly landing at end of October — cpldcpu · 2026-10-07
- Claude's "reasoning extraction" guardrail blocks users from seeing its thinking, and they're not happy — StewartalsopIII · 2026-10-07
- Grok's quirk: it says 'No.' then argues your point better than you did — gandamu_ml · 2026-10-07