Yhn SportCricket first seen 19 h ago, last 18 min ago, peak #9
iPhone used as second GPU to speed up local AI on MacBook
Original: I made my iPhone a second GPU for my MacBook-Qwen 3.8 27B prefills 29–44% faster
A developer reports using an iPhone as a second GPU alongside a MacBook, claiming that running Qwen 27B locally delivers 29–44% faster prefill times. The setup suggests consumer Apple devices can be combined to boost on-device AI inference, and readers are debating the method, its practicality, and what it means for running large language models outside data centers.
Why now: People are interested in cheap tricks to accelerate local LLM inference using hardware they already own.
Rank over time, top of the chart is #1. 31 snapshots from 19 h ago to 18 min ago.
Evidence
API: https://socialmediatrends-api.osmike.com/v1/trends/910157