<!--
{
  "availability" : [
    "iOS: 17.4.0 -",
    "iPadOS: 17.4.0 -",
    "macCatalyst: 17.4.0 -",
    "macOS: 14.4.0 -",
    "tvOS: 17.4.0 -",
    "visionOS: 1.0.0 -",
    "watchOS: 10.4.0 -"
  ],
  "documentType" : "symbol",
  "framework" : "CoreML",
  "identifier" : "/documentation/CoreML/MLComputePlan-1w21n/load(contentsOf:configuration:)",
  "metadataVersion" : "0.1.0",
  "role" : "Type Method",
  "symbol" : {
    "kind" : "Type Method",
    "modules" : [
      "Core ML"
    ],
    "preciseIdentifier" : "s:6CoreML13MLComputePlanC4load10contentsOf13configurationAC10Foundation3URLV_So20MLModelConfigurationCtYaKFZ"
  },
  "title" : "load(contentsOf:configuration:)"
}
-->

# load(contentsOf:configuration:)

Construct the compute plan of a model asynchronously given the location of its on-disk representation.

```
static func load(contentsOf url: URL, configuration: MLModelConfiguration) async throws -> MLComputePlan
```

## Parameters

`url`

The on-disk location of the compiled model (.mlmodelc directory).

`configuration`

The model configuration.

---

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)