EmbeddingGemma 2 runs offline multimodal RAG on phones in ~191MB–567MB of RAM
Saboo_Shubham_ · x · 2026-10-07
- Claims fully offline, free multimodal RAG on phones
- 191MB RAM for text-only search; 567MB for text + image + video + audio, measured on a Pixel 11 Pro
- Open weights under Apache 2.0
More from Infra
- One RTX Pro 6K Sidecar Lifts DGX Station GB300 to 60K tok/s Prefill with DeepSeek V4.1 Flash — Sentdex · 2026-10-07
- Hugging Face's Talk: A Full Tour of llama.cpp and the Local AI Inference Ecosystem — unofficialmerve · 2026-10-07
- Constellation Energy stock surges 14% on 20-year nuclear power deal with Google — Polymarket · 2026-10-07
- DNS root KSK rollover hits October 11: Cloudflare explains KSK-2024 switch and readiness test — Cloudflare Blog · 2026-10-07
- Qwen3.8 Flash Next IQ1_M hits 55 tok/s on a 5060 Ti 16GB and still codes well — bobaburger · 2026-10-07
- Qwen 3.8 27B hits 96 t/s decode with 110k context on a single 16GB RTX 5080 via NInfer — Kernoriordan · 2026-10-07