Local AI setup proves exciting but frustrating for a Verge reporter
Overview
A Verge reporter moves personal AI tasks off cloud services and onto local models, reports The Verge.
The reporter runs the open-source Hermes Agent on a Mac Studio with 256GB of unified memory, with the first model being Qwen 3.8 Flash Next, a 125-billion-parameter model of about 105GB. The reporter controls the setup from a phone through a Telegram bot. Early tasks include a morning briefing cron job and sorting over 400 Steam games into genre categories, a job that used a Steam web API key which was later revoked.
Written by AI from the articles below · updated Oct 11, 7:32 AM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- The Verge · AINewsLearning to use local AI is exciting, overwhelming, and frustrating
AIThe Verge's reporter starts using local AI models to avoid sending personal data to cloud services, running the open-source Hermes Agent on a Mac Studio with 256GB of unified memory. The first model is Qwen 3.8 Flash Next, a 125-billion-parameter model around 105GB in size, which the reporter controls from a phone through a Telegram bot. Early tasks include a morning briefing cron job and sorting over 400 Steam games into genre categories using a Steam web API key that was revoked afterward.
Heat trend
Not enough continuous observations to show a trend yet.