GoKawiilLaya OS Jev runs offline on Apple M4 via CoreML at 45 decisions per second
A developer has demonstrated Laya, referred to as 'OS Jev', running fully offline on Apple's M4 chip using Apple's CoreML framework. The system reportedly processes 45 decisions per second locally, without needing a cloud connection or internet access.
GoKawiil's interpretation of the reporting above, not reported fact.
Running AI decision-making entirely on-device removes latency and privacy concerns tied to cloud-based inference, and shows Apple silicon's growing capability for local AI workloads. This kind of offline throughput could make real-time, always-available AI agents more practical on consumer hardware.
- Laya (OS Jev) operates fully offline on Apple M4 hardware
- CoreML is used to achieve local inference without cloud dependency
- The system achieves 45 decisions per second in this demonstration
Apple Mac Mini M4 — If you're running CoreML workloads offline like this Laya OS Jev demo, the M4 chip's neural engine is exactly the kind of hardware that makes local inference fast and efficient. The Mac Mini M4 offers that same Apple Silicon performance in a compact, affordable desktop form factor, great for developers experimenting with on-device machine learning models.
See Apple Mac Mini M4 on Amazon → Affiliate link — we may earn a commission on purchases, at no extra cost to you. Product picked by AI based on this article; it is not a tested recommendation.Source: gist.github.com, 2026-09-20
Published there as: “Laya (OS Jev) on Mac M4 CoreML Offline (45 decisions per second)”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.