---
title: "Apple's 'Minions' runs AI inference on idle Macs"
url: https://www.parallelquant.com/posts/apple-s-minions-runs-ai-inference-on-idle-macs-71821a
source_name: "Tom's Hardware"
source_url: https://www.tomshardware.com/tech-industry/artificial-intelligence/apple-researchers-turn-idle-macs-into-a-virtual-gpu-cloud-with-minions-researchers-say-the-distributed-scheme-could-scale-globally-and-support-model-training
published: 2026-10-14T11:15:00.000Z
topics: ["chips", "research"]
publisher: "Parallel Quant"
---

# Apple's 'Minions' runs AI inference on idle Macs

*2026-10-14 · Source: [Tom's Hardware](https://www.tomshardware.com/tech-industry/artificial-intelligence/apple-researchers-turn-idle-macs-into-a-virtual-gpu-cloud-with-minions-researchers-say-the-distributed-scheme-could-scale-globally-and-support-model-training)*

Apple researchers describe Minions, an internal system that runs AI inference jobs on idle Apple Silicon Macs when GPUs are scarce.

**Why it matters:** It shows a large company treating its installed base of consumer hardware as spare inference capacity, an alternative to competing for scarce data-center GPUs. That echoes Anthropic's finding on small models running on consumer devices, and suggests distributed inference could ease supply pressure.

**Topics:** chips, research

---
Read the original: https://www.tomshardware.com/tech-industry/artificial-intelligence/apple-researchers-turn-idle-macs-into-a-virtual-gpu-cloud-with-minions-researchers-say-the-distributed-scheme-could-scale-globally-and-support-model-training
Canonical: https://www.parallelquant.com/posts/apple-s-minions-runs-ai-inference-on-idle-macs-71821a
Published by Parallel Quant — https://www.parallelquant.com