<!--
{
  "availability" : [
    "iOS: 15.0.0 - 17.4.0",
    "iPadOS: 15.0.0 - 17.4.0",
    "macCatalyst: 15.0.0 - 17.4.0",
    "macOS: 12.0.0 - 14.3.0",
    "tvOS: 15.0.0 - 17.4.0"
  ],
  "documentType" : "symbol",
  "framework" : "MLCompute",
  "identifier" : "/documentation/MLCompute/MLCLayer/deviceType",
  "metadataVersion" : "0.1.0",
  "role" : "Instance Property",
  "symbol" : {
    "kind" : "Instance Property",
    "modules" : [
      "ML Compute"
    ],
    "preciseIdentifier" : "c:objc(cs)MLCLayer(py)deviceType"
  },
  "title" : "deviceType"
}
-->

# deviceType

A device type that indicates where the system executes the layer.

```
var deviceType: MLCDeviceType { get }
```

## Discussion

The system uses the [`MLCDevice`](/documentation/MLCompute/MLCDevice) you provide to [`compile(options:device:)`](/documentation/MLCompute/MLCTrainingGraph/compile(options:device:)) to execute the layers in the graph.

If you select [`MLCDeviceType.ane`](/documentation/MLCompute/MLCDeviceType/ane), it is possible that some layers may not execute on the [`MLCDeviceType.ane`](/documentation/MLCompute/MLCDeviceType/ane), but instead on the CPU or GPU.

---

Copyright &copy; 2026 Apple Inc. All rights reserved. | [Terms of Use](https://www.apple.com/legal/internet-services/terms/site.html) | [Privacy Policy](https://www.apple.com/privacy/privacy-policy)