Is Private Cloud Compute allowed? Or are on-device Foundational Models allowed only? Thanks!

During testing the “Bringing advanced speech-to-text capabilities to your app” sample app demonstrating the use of iOS 26 SpeechAnalyzer, I noticed that the language model for the English locale was presumably already downloaded. Upon checking the documentation of AssetInventory, I found out that indeed, the language model can be preinstalled on the system. Can someone from the dev team share more info about what assets are preinstalled by the system? For example, can we safely assume that the English language model will almost certainly be already preinstalled by the OS if the phone has the English locale?

I’m sure someone though about it already. But let’s have ecosystem, where Apple Intelligence uses your most capable (Apple) hardware at first and the cloud service as second.

Is the face and body detection service in the Vision framework a local model or a cloud model? Is there a performance report? https://aninterestingwebsite.com/documentation/vision

At WWDC25 we launched a new type of Lab event for the developer community - Group Labs. A Group Lab is a panel Q&A designed for a large audience of developers. Group Labs are a unique opportunity for the community to submit questions directly to a panel of Apple engineers and designers. Here are the highlights from the WWDC25 Group Lab for Machine Learning and AI Frameworks. What are you most excited about in the Foundation Models framework? The Foundation Models framework provides access to an on-device Large Language Model (LLM), enabling entirely on-device processing for intelligent features. This allows you to build features such as personalized search suggestions and dynamic NPC generation in games. The combination of guided generation and streaming capabilities is particularly exciting for creating delightful animations and features with reliable output. The seamless integration with SwiftUI and the new design material Liquid Glass is also a major advantage. When should I still bring my own LLM via CoreML? It's generally recommended to first explore Apple's built-in system models and APIs, including the Foundation Models framework, as they are highly optimized for Apple devices and cover a wide range of use cases. However, Core ML is still valuable if you need more control or choice over the specific model being deployed, such as customizing existing system models or augmenting prompts. Core ML provides the tools to get these models on-device, but you are responsible for model distribution and updates. Should I migrate PyTorch code to MLX? MLX is an open-source, general-purpose machine learning framework designed for Apple Silicon from the ground up. It offers a familiar API, similar to PyTorch, and supports C, C++, Python, and Swift. MLX emphasizes unified memory, a key feature of Apple Silicon hardware, which can improve performance. It's recommended to try MLX and see if its programming model and features better suit your application's needs. MLX shines when working with state-of-the-art, larger models. Can I test Foundation Models in Xcode simulator or device? Yes, you can use the Xcode simulator to test Foundation Models use cases. However, your Mac must be running macOS Tahoe. You can test on a physical iPhone running iOS 18 by connecting it to your Mac and running Playgrounds or live previews directly on the device. Which on-device models will be supported? any open source models? The Foundation Models framework currently supports Apple's first-party models only. This allows for platform-wide optimizations, improving battery life and reducing latency. While Core ML can be used to integrate open-source models, it's generally recommended to first explore the built-in system models and APIs provided by Apple, including those in the Vision, Natural Language, and Speech frameworks, as they are highly optimized for Apple devices. For frontier models, MLX can run very large models. How often will the Foundational Model be updated? How do we test for stability when the model is updated? The Foundation Model will be updated in sync with operating system updates. You can test your app against new model versions during the beta period by downloading the beta OS and running your app. It is highly recommended to create an "eval set" of golden prompts and responses to evaluate the performance of your features as the model changes or as you tweak your prompts. Report any unsatisfactory or satisfactory cases using Feedback Assistant. Which on-device model/API can I use to extract text data from images such as: nutrition labels, ingredient lists, cashier receipts, etc? Thank you. The Vision framework offers the RecognizeDocumentRequest which is specifically designed for these use cases. It not only recognizes text in images but also provides the structure of the document, such as rows in a receipt or the layout of a nutrition label. It can also identify data like phone numbers, addresses, and prices. What is the context window for the model? What are max tokens in and max tokens out? The context window for the Foundation Model is 4,096 tokens. The split between input and output tokens is flexible. For example, if you input 4,000 tokens, you'll have 96 tokens remaining for the output. The API takes in text, converting it to tokens under the hood. When estimating token count, a good rule of thumb is 3-4 characters per token for languages like English, and 1 character per token for languages like Japanese or Chinese. Handle potential errors gracefully by asking for shorter prompts or starting a new session if the token limit is exceeded. Is there a rate limit for Foundation Models API that is limited by power or temperature condition on the iPhone? Yes, there are rate limits, particularly when your app is in the background. A budget is allocated for background app usage, but exceeding it will result in rate-limiting errors. In the foreground, there is no rate limit unless the device is under heavy load (e.g., camera open, game mode). The system dynamically balances performance, battery life, and thermal conditions, which can affect the token throughput. Use appropriate quality of service settings for your tasks (e.g., background priority for background work) to help the system manage resources effectively. Do the foundation models support languages other than English? Yes, the on-device Foundation Model is multilingual and supports all languages supported by Apple Intelligence. To get the model to output in a specific language, prompt it with instructions indicating the user's preferred language using the locale API (e.g., "The user's preferred language is en-US"). Putting the instructions in English, but then putting the user prompt in the desired output language is a recommended practice. Are larger server-based models available through Foundation Models? No, the Foundation Models API currently only provides access to the on-device Large Language Model at the core of Apple Intelligence. It does not support server-side models. On-device models are preferred for privacy and for performance reasons. Is it possible to run Retrieval-Augmented Generation (RAG) using the Foundation Models framework? Yes, it is possible to run RAG on-device, but the Foundation Models framework does not include a built-in embedding model. You'll need to use a separate database to store vectors and implement nearest neighbor or cosine distance searches. The Natural Language framework offers simple word and sentence embeddings that can be used. Consider using a combination of Foundation Models and Core ML, using Core ML for your embedding model.

I'm using a custom create ML model to classify the movement of a user's hand in a game, The classifier has 3 different spell movements, but my code constantly predicts all of them at an equal 1/3 probability regardless of movement which leads me to believe my code isn't correct (as opposed to the model) which in CreateML at least gives me a heavily weighted prediction My code is below. On adding debug prints everywhere all the data looks good to me and matches similar to my test CSV data So I'm thinking my issue must be in the setup of my model code? /// Feeds samples into the model and keeps a sliding window of the last N frames. final class WandGestureStreamer { static let shared = WandGestureStreamer() private let model: SpellActivityClassifier private var samples: [Transform] = [] private let windowSize = 100 // number of frames the model expects /// RNN hidden state passed between inferences private var stateIn: MLMultiArray /// Last transform dropped from the window for continuity private var lastDropped: Transform? private init() { let config = MLModelConfiguration() self.model = try! SpellActivityClassifier(configuration: config) // Initialize stateIn to the model’s required shape let constraint = self.model.model.modelDescription .inputDescriptionsByName["stateIn"]! .multiArrayConstraint! self.stateIn = try! MLMultiArray(shape: constraint.shape, dataType: .double) } /// Call once per frame with the latest wand position (or any feature vector). func appendSample(_ sample: Transform) { samples.append(sample) // drop oldest frame if over capacity, retaining it for delta at window start if samples.count > windowSize { lastDropped = samples.removeFirst() } } func classifyIfReady(threshold: Double = 0.6) -> (label: String, confidence: Double)? { guard samples.count == windowSize else { return nil } do { let input = try makeInput(initialState: stateIn) let output = try model.prediction(input: input) // Save state for continuity stateIn = output.stateOut let best = output.label let conf = output.labelProbability[best] ?? 0 // If you’ve recognized a gesture with high confidence: if conf > threshold { return (best, conf) } else { return nil } } catch { print("Error", error.localizedDescription, error) return nil } } /// Constructs a SpellActivityClassifierInput from recorded wand transforms. func makeInput(initialState: MLMultiArray) throws -> SpellActivityClassifierInput { let count = samples.count as NSNumber let shape = [count] let timeArr = try MLMultiArray(shape: shape, dataType: .double) let dxArr = try MLMultiArray(shape: shape, dataType: .double) let dyArr = try MLMultiArray(shape: shape, dataType: .double) let dzArr = try MLMultiArray(shape: shape, dataType: .double) let rwArr = try MLMultiArray(shape: shape, dataType: .double) let rxArr = try MLMultiArray(shape: shape, dataType: .double) let ryArr = try MLMultiArray(shape: shape, dataType: .double) let rzArr = try MLMultiArray(shape: shape, dataType: .double) for (i, sample) in samples.enumerated() { let previousSample = i > 0 ? samples[i - 1] : lastDropped let model = WandMovementRecording.DataModel(transform: sample, previous: previousSample) // print("model", model) timeArr[i] = NSNumber(value: model.timestamp) dxArr[i] = NSNumber(value: model.dx) dyArr[i] = NSNumber(value: model.dy) dzArr[i] = NSNumber(value: model.dz) let rot = model.rotation rwArr[i] = NSNumber(value: rot.w) rxArr[i] = NSNumber(value: rot.x) ryArr[i] = NSNumber(value: rot.y) rzArr[i] = NSNumber(value: rot.z) } return SpellActivityClassifierInput( dx: dxArr, dy: dyArr, dz: dzArr, rotation_w: rwArr, rotation_x: rxArr, rotation_y: ryArr, rotation_z: rzArr, timestamp: timeArr, stateIn: initialState ) } }

Pretty much as per the title and I suspect I know the answer. Given that Foundation Models run on device, is it possible to use Foundation Models framework inside of a DeviceActivityReport? I've been tinkering with it, and all I get is errors and "Sandbox restrictions". Am I missing something? Seems like a missed trick to utilise on device AI/ML with other frameworks.

I've been successfully integrating the Foundation Models framework into my healthcare app using structured generation with @Generable schemas. While my initial testing (20-30 iterations) shows promising results, I need to validate consistency and reliability at scale before production deployment. Question Is there a recommended approach for automated, large-scale testing of Foundation Models responses? Specifically, I'm looking to: Automate 1000+ test iterations with consistent prompts and structured schemas Measure response consistency across identical inputs Validate structured output reliability (proper schema adherence, no generation failures) Collect performance metrics (TTFT, TPS) for optimization Specific Questions Framework Limitations: Are there any undocumented rate limits or thermal throttling considerations for rapid session creation/destruction? Performance Tools: Can Xcode's Foundation Models Instrument be used programmatically, or only through Instruments UI? Automation Integration: Any recommendations for integrating with testing frameworks? Session Reuse: Is it better to reuse a single LanguageModelSession or create fresh sessions for each test iteration? Use Case Context My wellness app provides medically safe activity recommendations based on user health profiles. The Foundation Models framework processes health context and generates structured recommendations for exercises, nutrition, and lifestyle activities. Given the safety implications of providing health-related guidance, I need rigorous validation to ensure the model consistently produces appropriate, well-formed recommendations across diverse user scenarios and health conditions. Has anyone in the community built similar large-scale testing infrastructure for Foundation Models? Any insights on best practices or potential pitfalls would be greatly appreciated.

Apologies if this is obvious to everyone but me... I'm using the Tahoe AI foundation models. When I get an error, I'm trying to handle it properly. I see the errors described here: https://aninterestingwebsite.com/documentation/foundationmodels/languagemodelsession/generationerror/context, as well as in the headers. But all I can figure out how to see is error.localizedDescription which doesn't give me much to go on. For example, an error's description is: The operation couldn’t be completed. (FoundationModels.LanguageModelSession.GenerationError error 2. That doesn't give me much to go on. How do I get the actual error number/enum value out of this, short of parsing that text to look for the int at the end? This one is: case guardrailViolation(LanguageModelSession.GenerationError.Context) So I'd like to know how to get from the catch for session.respond to something I can act on. I feel like it's there, but I'm missing it. Thanks!

Hello, Could you please provide details for maximum string length of the prompt and the title when using ImageCreator and the method extracted(from:title:)? static func extracted( from text: String, title: String? = nil ) -> ImagePlaygroundConcept Any additional details or example of prompt and title would help. Additionally, are ImagePlaygroundStyle.animation, ImagePlaygroundStyle.illustration and ImagePlaygroundStyle.sketch all available when using extracted(from:title:)? I am trying to generate images programmatically and would appreciate your guidance. Thank you.

Hello, I am developing an iOS app that uses machine learning models. To improve accuracy and user experience, I would like to download .mlmodel files (compiled and compressed as zip files) from our own server after the app is installed, and use them for inference within the app. No executable code, scripts, or dynamic libraries will be downloaded—only model data files are used. According to App Store Review Guideline 2.5.2, I understand that apps may not download or execute code which introduces or changes features or functionality. In this case, are compiled and zip-compressed .mlmodel files considered "data" rather than "code", and is it allowed to download and use them in the app? If there are any restrictions or best practices related to this, please let me know. Thank you.

Does CoreML object detection only support AABB (Axis-Aligned Bounding Boxes) or also OBB (Oriented Bounded Boxes)? If not, any way to do it using Apple frameworks?

Hi everyone 👋 I'd like to use coremltools to see how well a model performs on a remote device as part of a CI/CD pipeline. According to the Core ML Tools "Debugging and Performance Utilities" guide, remote devices must be in a "connected" state in order for coremltools to install the ModelRunner application. The devices in our system have a "paired" state, and I'm unable to set the them as "connected." The only way I know how to connect a device is to physically plug it in to a computer and open Xcode. I don't have physical access to the devices in the CI/CD system, and the host computer that interacts with them doesn't have Xcode installed. Here are some questions I've been looking into and would love some help answering: Has anyone managed to use the coremltools performance utilities in a similar system? Can you put a device in a "connected" state if you don't have physical access to the device and if you only have access to Xcode command line tools and not the Xcode app? Is it at all possible to install the coremltools ModelRunner application on a "paired" device, for example, by manually building the app and installing it with devicectl? Would other utilities, such as the MLModelBenchmarker work as expected if the app is installed this way? Thank you!

Encountered a few times when the answer get "stuck" (I am now at beta 6). This is an example.

Hi, I’m developing an app targeting iOS 26, using the new FoundationModels framework to perform on-device LLM inference. I’m currently testing memory usage. Does the memory used by FoundationModels—including model weights, KV cache, and any inference-related buffers—count toward my app’s Jetsam memory limit, or is any of it managed separately by the system? I may need to run two concurrent inferences, each with a 4096-token context window. Is this explicitly supported or allowed by FoundationModels on iOS 26? Would this significantly increase the risk of memory-based termination? Thanks in advance for any clarification. Thanks.

Hey, When generating responses with structured output and non-streaming API, it sometimes takes 3s, sometimes 10-20s. I am firing that request subsequently while testing the app. Is this by design, or any place I can learn more about what contributes to such variation?

Looking for help with or to help with, due to the pending document enhancement, the Vibe Coders edition of cml editor. Also for more information on how to use the .mlkey whether or not my model is suppose to say IOs18 when I am planning to use it on Mac Apple Intelligence seems to think coreML is for iOS but are the capabilities extended when running NPU on the book? How to use this graph. coming in hot sorry. btw. there are 100s of feedback and crash reports sent in form me for additional info? I attached a image that might help with updating Tags

In WWDC25 Metal 4 released quite excited new features for machine learning optimization, but as we all know the pytorch based on metal shader performance (mps) is the one of most important tools for Mac machine learning area.but on mps introduced website we cannot see any support information for metal4.

From tensorflow-metal example: Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 0 MB memory) -> physical PluggableDevice (device: 0, name: METAL, pci bus id: ) I know that Apple silicon uses UMA, and that memory copies are typical of CUDA, but wouldn't the GPU memory still be faster overall? I have an iMac Pro with a Radeon Pro Vega 64 16 GB GPU and an Intel iMac with a Radeon Pro 5700 8 GB GPU. But using tensorflow-metal is still WAY faster than using the CPUs. Thanks for that. I am surprised the 5700 is twice as fast as the Vega though.

When I initialize a session with an existing transcript using this initializer: public convenience init(model: SystemLanguageModel = .default, guardrails: LanguageModelSession.Guardrails = .default, tools: [any Tool] = [], transcript: Transcript) The tools get ignored. I noticed that when doing that, the model never use the tools. When inspecting the transcript, I can see that the instruction entry does not have any tools available to it. I tried this for both transcripts that already include an instruction entry and ones that don't - both yielding the same result.. Is this the intended behavior / am I missing something here?