Using idle Macs and GPUs as shared AI work nodes
Idle gaming PCs, workstations, and Macs could be used for AI work during the hours when they are not busy. The experiment turns spare GPUs and Macs into that handle LLM requests and requests through a single API.
The aim is not to replace local , but to put unused hardware to work. The practical question is whether people would let spare compute from a homelab or workstation serve outside requests when the machine is otherwise idle, and why they would or would not do it.
Key points
- Spare GPUs and Macs are being tested as nodes.
- LLM and requests would go through a single API.
- The goal is to use idle hardware, not to replace local .
- The open question is whether homelab owners would share spare compute when machines are idle.
- owners should think about security, power use, heat, and control before joining this kind of setup.