> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/argmaxinc/WhisperKit/llms.txt
> Use this file to discover all available pages before exploring further.

# ModelComputeOptions

> Configure compute units for WhisperKit model components

`ModelComputeOptions` configures which compute units (CPU, GPU, Neural Engine) are used for each component of the WhisperKit transcription pipeline.

## Overview

WhisperKit models consist of multiple components that can run on different compute units. `ModelComputeOptions` allows fine-grained control over where each component executes for optimal performance.

## Properties

<ResponseField name="melCompute" type="MLComputeUnits" default=".cpuAndGPU">
  Compute units for mel spectrogram generation.
</ResponseField>

<ResponseField name="audioEncoderCompute" type="MLComputeUnits" default=".cpuAndNeuralEngine (iOS 17+/macOS 14+) or .cpuAndGPU">
  Compute units for audio encoding. Defaults to Neural Engine on newer OS versions for better performance.
</ResponseField>

<ResponseField name="textDecoderCompute" type="MLComputeUnits" default=".cpuAndNeuralEngine">
  Compute units for text decoding.
</ResponseField>

<ResponseField name="prefillCompute" type="MLComputeUnits" default=".cpuOnly">
  Compute units for KV cache prefill operations.
</ResponseField>

## Initialization

```swift theme={null}
public init(
    melCompute: MLComputeUnits = .cpuAndGPU,
    audioEncoderCompute: MLComputeUnits? = nil,
    textDecoderCompute: MLComputeUnits = .cpuAndNeuralEngine,
    prefillCompute: MLComputeUnits = .cpuOnly
)
```

### Parameters

<ParamField path="melCompute" type="MLComputeUnits" default=".cpuAndGPU">
  Compute units for mel spectrogram extraction.
</ParamField>

<ParamField path="audioEncoderCompute" type="MLComputeUnits" default="nil">
  Compute units for audio encoding. When `nil`, automatically selects `.cpuAndNeuralEngine` on iOS 17+/macOS 14+ and `.cpuAndGPU` on older versions.
</ParamField>

<ParamField path="textDecoderCompute" type="MLComputeUnits" default=".cpuAndNeuralEngine">
  Compute units for text decoding.
</ParamField>

<ParamField path="prefillCompute" type="MLComputeUnits" default=".cpuOnly">
  Compute units for prefill operations.
</ParamField>

## MLComputeUnits Values

Apple's `MLComputeUnits` enum specifies which processors can execute a Core ML model:

* `.cpuOnly` - Only the CPU
* `.cpuAndGPU` - CPU and GPU
* `.cpuAndNeuralEngine` - CPU and Neural Engine (recommended for most models)
* `.all` - All available compute units

## Usage Examples

### Default Configuration

```swift theme={null}
let options = ModelComputeOptions()
// Uses optimal defaults for your device
```

### Custom Configuration

```swift theme={null}
let options = ModelComputeOptions(
    melCompute: .cpuAndGPU,
    audioEncoderCompute: .cpuAndNeuralEngine,
    textDecoderCompute: .cpuAndNeuralEngine,
    prefillCompute: .cpuOnly
)

let config = WhisperKitConfig(
    model: "openai_whisper-base",
    computeOptions: options
)

let whisperKit = try await WhisperKit(config)
```

### Force CPU-Only Execution

```swift theme={null}
let cpuOnlyOptions = ModelComputeOptions(
    melCompute: .cpuOnly,
    audioEncoderCompute: .cpuOnly,
    textDecoderCompute: .cpuOnly,
    prefillCompute: .cpuOnly
)
```

## Simulator Handling

When running on the iOS Simulator, all compute options are automatically overridden to `.cpuOnly` since the simulator doesn't support GPU or Neural Engine execution.

## Performance Considerations

### Neural Engine

The Neural Engine provides the best performance for most Whisper models on Apple Silicon devices:

* Recommended for `audioEncoderCompute` and `textDecoderCompute`
* Requires iOS 17+/macOS 14+ for optimal audio encoder performance
* Most efficient for battery-powered devices

### GPU

The GPU can be beneficial for certain operations:

* Recommended for `melCompute` on most devices
* May provide better throughput on some Mac models
* Consider for batch processing scenarios

### CPU Only

CPU-only execution:

* Required for `prefillCompute` operations
* Use when Neural Engine/GPU are unavailable
* May be necessary for debugging or compatibility

## Related Types

* [WhisperKitConfig](/api/core/whisperkit-config)
* [ModelState](/api/core/model-state)