License: MIT Framework Platform Xcode iOS Apple

Localight is a simple SwiftUI chatbot app for iOS 26 and iOS 27, powered entirely by Apple’s on-device Foundation Models. Designed for demonstration purposes, Localight offers fast, private, and completely offline AI chat — no internet connection or server required.

Localight showcases how to integrate Apple's local LLM into a native iOS experience using SwiftUI and the new Foundation Models framework.

⚠️ Disclaimer: This app is for demonstration purposes only and is not production-ready. Output generated by the local large language model may be inaccurate, incomplete, or misleading.

Apple’s third-generation model family contains five models: two on-device models and three server-based models running on Private Cloud Compute. The local models are AFM 3 Core, a dense 3-billion-parameter model, and AFM 3 Core Advanced, a multimodal 20-billion-parameter sparse model that activates 1–4 billion parameters depending on the request. The server models are AFM 3 Cloud, ADM 3 Cloud (Image), and AFM 3 Cloud Pro.

Localight accesses the system-provided on-device model through SystemLanguageModel. Availability depends on the device and operating system. See Introducing the Third Generation of Apple’s Foundation Models for details.

• 🧠 On-device LLM: Uses Apple’s local Foundation Models for text generation.
• 🔐 Privacy-first: All conversations stay on your device. No data is sent to the cloud.
• ⚡ Fast & Offline: No internet needed. Responses are generated locally.
• 💬 Minimalist Chat UI: Clean SwiftUI interface for interacting with the model.
• 🗑️ No history: Conversation is not saved after closing the app.

Localight keeps separate implementations for each supported iOS version:

Localight/
├── ContentView_26.swift
├── ContentView_27.swift
├── iOS_26/ # iOS 26 chat, model, settings, and components
├── iOS_27/ # iOS 27 chat, model, settings, and components
└── LocalightApp.swift # Selects the implementation for the current iOS version

Version-specific files and types use the _26 or _27 suffix.

• Import the Library: To work with Foundation Models, you must import the library in every file where you intend to use them. Go with:

  import FoundationModels

• Check Availability: The key object is the SystemLanguageModel. This can indicate whether the model is .available or .unavailable. In case of unavailability, a reason is also provided.

• Create a LanguageModelSession: To start prompting, create a LanguageModelSession. Its instructions define the model’s role and response behavior:

  let session = LanguageModelSession(instructions: "You are the best friend.")

• Generate a Response: Finally, call the method to receive a result as a String by using:

  let response = try await session.respond(to: promptAsString).content

• Stream a Response: Otherwise, you can call the method to receive a result as a String that is streamed by using:

  let stream = session.streamResponse(to: promptAsString)
  do {
   for try await chunk in stream {
   self.streamingResponse = chunk.content
   }
   
   let response = try await stream.collect().content
  } catch {}

• Handle Generation Errors: On iOS 27, Localight maps LanguageModelError cases such as context-size, rate-limit, timeout, refusal, guardrail, and unsupported-content failures to user-facing alerts instead of adding raw framework errors to the chat.

Apple’s on-device Foundation Models operate with a limited context window per session. The context window defines how many tokens the model can process within a single LanguageModelSession. On iOS 27, the displayed usage includes the system instructions.

• A token is a unit of text processed by the model.
• In Western languages (e.g. English or German), 1 token ≈ 3–4 characters.
• In East Asian languages (e.g. Japanese or Chinese), 1 token ≈ 1 character.
• The system model currently supports up to 4,096 tokens per session.

If this limit is exceeded, the framework throws the following error: LanguageModelError.contextSizeExceeded(_:)

For more details, see Apple’s official documentation: TN3193 – Managing the on-device foundation model’s context window

Localight is available under the MIT License. See LICENSE for the full license text.