RF-DETR runs fully offline on iPhone 17 with real-time detection in SwiftUI
amos_gyamfi · x · 2026-11-19
Developer amosgyamfi demonstrated running Roboflow's RF-DETR entirely on-device on an iPhone 17, achieving real-time detection and segmentation in a SwiftUI app with no token costs, no API subscription, and no internet connection.
The model comes from the coreai-model-zoo GitHub repo (466 stars), which offers downloadable models and conversion recipes for Apple's Core AI on iPhone and Mac — spanning chat, vision, speech, and generative models, with per-model validation records, Swift examples via CoreAIKit, and a downloadable Mac app.
More from Infra
- Local MiniMax H3 on 6GB VRAM: 50 minutes tuned vs 6.5 hours on defaults — No_Cow26 · 2026-11-19
- Compress Wikipedia to ~27GB locally: neural compression via tufazip — Terminator857 · 2026-11-19
- One GPU transcribes 8.7 hours of mock GP calls in 18 minutes, 27.8x realtime — MaziyarPanahi · 2026-11-19
- Ramp AI Index: token prices down 21.2% in six weeks, Anthropic holds 58.7% of spend — RebeccaBellan · 2026-11-19
- US Army Europe-Africa open-sources goatcore, a self-hosted data fabric built for offline use — victorialslocum · 2026-11-19
- XBOW publishes Java4Shell CPU compatibility matrix covering 10 cloud providers — moyix · 2026-11-19