# Options

    public struct Options : Equatable, Hashable

Options for configuring the `https://developers.google.com/edge/api/tflite/swift/Classes/MetalDelegate.html`.
- `


  ### [isPrecisionLossAllowed](https://developers.google.com/edge/api/tflite/swift/Classes/MetalDelegate/Options#/s:19TensorFlowLiteSwift13MetalDelegateC7OptionsV22isPrecisionLossAllowedSbvp)


  ` Indicates whether the GPU delegate allows precision loss, such as allowing `Float16`
  precision for a `Float32` computation. The default is `false`.

  #### Declaration

  Swift

      public var isPrecisionLossAllowed: Bool

- `


  ### [allowsPrecisionLoss](https://developers.google.com/edge/api/tflite/swift/Classes/MetalDelegate/Options#/s:19TensorFlowLiteSwift13MetalDelegateC7OptionsV19allowsPrecisionLossSbvp)


  ` Undocumented

  #### Declaration

  Swift

      public var allowsPrecisionLoss: Bool { get set }

- `


  ### [waitType](https://developers.google.com/edge/api/tflite/swift/Classes/MetalDelegate/Options#/s:19TensorFlowLiteSwift13MetalDelegateC7OptionsV8waitTypeAA010ThreadWaitI0Ovp)


  ` A type indicating how the current thread should wait for work on the GPU to complete. The
  default is `passive`.

  #### Declaration

  Swift

      public var waitType: https://developers.google.com/edge/api/tflite/swift/Enums/ThreadWaitType.html

- `


  ### [isQuantizationEnabled](https://developers.google.com/edge/api/tflite/swift/Classes/MetalDelegate/Options#/s:19TensorFlowLiteSwift13MetalDelegateC7OptionsV21isQuantizationEnabledSbvp)


  ` Indicates whether the GPU delegate allows execution of an 8-bit quantized model. The default
  is `true`.

  #### Declaration

  Swift

      public var isQuantizationEnabled: Bool

- `


  ### [init()](https://developers.google.com/edge/api/tflite/swift/Classes/MetalDelegate/Options#/s:19TensorFlowLiteSwift13MetalDelegateC7OptionsVAEycfc)


  ` Creates a new instance with the default values.

  #### Declaration

  Swift

      public init()