Laya (OS Jev) on Mac M4 CoreML Offline (45 decisions per second)

A gist shows the Laya (OS Jev) model running fully offline on an Apple M4 Mac via CoreML at 45 decisions per second.

A developer-published gist describes running Laya (OS Jev) entirely offline on Apple M4 silicon using the CoreML framework. The setup reportedly achieves 45 decisions per second, indicating use as an on-device decision-making or agent engine. The available text provides no model size, weights, or benchmark methodology details. It is a niche local-inference demo rather than a model release or research paper.

• Laya (OS Jev) runs fully offline on Apple M4 hardware via CoreML
• Reported throughput is 45 decisions per second on the local setup