---
title: deviceType
framework: ML Compute
role: symbol
role_heading: Instance Property
platforms: [iOS 15.0+, iPadOS 15.0+, Mac Catalyst 15.0+, macOS 12.0+, tvOS 15.0+]
path: mlcompute/mlclayer/devicetype
---

# deviceType

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

## Declaration

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

## Discussion

Discussion The system uses the MLCDevice you provide to compile(options:device:) to execute the layers in the graph. If you select MLCDeviceType.ane, it is possible that some layers may not execute on the MLCDeviceType.ane, but instead on the CPU or GPU.

## See Also

### Inspecting a Layer

- [layerID](mlcompute/mlclayer/layerid.md)
- [label](mlcompute/mlclayer/label.md)
- [isDebuggingEnabled](mlcompute/mlclayer/isdebuggingenabled.md)
- [supportsDataType(_:on:)](mlcompute/mlclayer/supportsdatatype(_:on:).md)