Perplexity goes local: private tasks hand off to on-device small models

HowDevelop · x · 2026-09-07

Perplexity's Aravind explained on CNBC why the company went local: frontier models stay in the cloud, but the moment a task touches health records or tax returns, it hands off to a smaller model on the user's own hardware.

This supports the view that every AI product ends up with a local half, driven by privacy first, cost second — and the hard part is running it on whatever machine the user already owns. The open-source goose-mobile-ondevice-llamacpp project demonstrates on-device agents with goose and Gemma on Qualcomm devices via llama.cpp, including an iOS client on the App Store and an experimental Android full-device automation PoC.

Original post →

More from coding & agent

coding & agent channel →