The fastest inference runtime for iPhone, iPad and Mac.

1import Uzu2​3public func runChat() async throws {4    let engineConfig = EngineConfig.create()5    let engine = try await Engine.create(config: engineConfig)6​7    guard let model = try await engine.model(identifier: "Qwen/Qwen3-0.6B") else {8        return9    }10    for try await update in try await engine.download(model: model).iterator() {11        print("Download progress: \(update.progress())")12    }13​14    let messages = [15        ChatMessage.system().withText(text: "You are a helpful assistant"),16        ChatMessage.user().withText(text: "Tell me a short, funny story about a robot")17    ]18    let session = try await engine.chat(model: model, config: .create())19    let stream = await session.replyWithStream(input: messages, config: .create())20    var message: ChatMessage? = nil21    for try await update in stream.iterator() {22        switch update {23        case .replies(let replies):24            message = replies.last?.message25        case .error(let error):26            print("Error: \(error)")27        }28    }29    print("Text: \(message?.text() ?? "empty")")30}