# load(contentsOf:configuration:completionHandler:) Creates a Core ML model instance asynchronously from a compiled model file, a custom configuration, and a completion handler. ``` class func load(contentsOf url: URL, configuration: MLModelConfiguration = MLModelConfiguration(), completionHandler handler: @escaping (Result) -> Void) ``` ## Parameters `url` The path to a compiled model file (*ModelName*`.mlmodelc`), typically with the `URL` that [`compileModel(at:)`](/documentation/CoreML/MLModel/compileModel(at:)-6442s) returns. `configuration` The runtime settings for the new model instance. `handler` A closure the method calls when it finishes loading the model. ## Discussion Use this method to load a model asynchronously. Core ML calls your completion handler after it successfully loads the model, or encounters an error attempting to load it. ```swift MLModel.load(contentsOf: modelURL) { result in switch result { case .success(let loadedModel): print("Successfully loaded model `\(loadedModel)`.") // Use the loaded model for predictions. // ... case .failure(let error): print("Error loading model: \(error).") } } ``` In Swift, if the model loaded successfully, you can use the instance from the associated value; otherwise, use the associated value to address the error. In Objective-C, you can use the [`MLModel`](/documentation/CoreML/MLModel) instance in your completion hander; otherwise, use the instance to address the error. See [`MLModelError.Code`](/documentation/CoreML/MLModelError-swift.struct/Code) for the list of error codes. --- Copyright © 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)