{
  "id": 14738106,
  "title": "Apple’s ‘Minions’ tech turns idle Macs into an AI data center",
  "url": "https://urgent.news/2026/10/15/apples-minions-tech-turns-idle-macs-into-an-ai-data-center",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-15T13:25:00.000Z",
  "source": {
    "name": "Computerworld",
    "slug": "computerworld",
    "url": "https://www.computerworld.com/article/4235901/apples-minions-tech-turns-idle-macs-into-an-ai-data-center.html"
  },
  "original_language": "en",
  "account": "Apple's internal technology, dubbed \"Minions,\" transforms idle Macs into a distributed virtual GPU cloud for AI inferencing tasks. A white paper outlines how this system can cut costs and improve efficiency for enterprises handling AI workloads. The Minions framework consists of three components: a Minion Server, Executor, and Watchdog. The server divides tasks and queues them, while the executor directs tasks across available Macs. The watchdog monitors tasks and ensures work continues even if a node goes offline. Minions supports GPU inference for embedding generation and LLM completions using open-source transformer models. Future plans include supporting distributed model training. Minions is particularly valuable in environments with constrained centralized GPU resources, allowing teams to tap into substantial compute capacity at no cost using existing hardware. The technology also helps avoid long queues for GPU compute and ensures data confidentiality through team- or organization-scoped deployments with dedicated PostgreSQL databases and isolated executor pools. While Apple hasn't announced plans to make Minions available outside the company, the potential for utilizing idle Macs in AI projects is significant, offering a cost-effective alternative to cloud-based inferencing.",
  "summary": "If your business has lots of Macs, what do you do with them at night? And how much money do you spend on AI inferencing? What if the computational power of those Macs could be used to handle some inferencing tasks ? A new white paper from Apple’s machine learning team tells us it’s possible. Apple’s teams have developed an internal technology for distributed processing they call “Minions,” which…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}