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.

Incident Identifier: 4C22F586-71FB-4644-B823-A4B52D158057 CrashReporter Key: adc89b7506c09c2a6b3a9099cc85531bdaba9156 Hardware Model: Mac16,10 Process: PRISMLensCore [16561] Path: /Applications/PRISMLens.app/Contents/Resources/app.asar.unpacked/node_modules/core-node/PRISMLensCore.app/PRISMLensCore Identifier: com.prismlive.camstudio Version: (null) ((null)) Code Type: ARM-64 Parent Process: ? [16560] Date/Time: (null) OS Version: macOS 15.4 (24E5228e) Report Version: 104 Exception Type: EXC_CRASH (SIGABRT) Exception Codes: 0x00000000 at 0x0000000000000000 Crashed Thread: 34 Application Specific Information: *** Terminating app due to uncaught exception 'NSInvalidArgumentException', reason: '*** -[__NSArrayM insertObject:atIndex:]: object cannot be nil' Thread 34 Crashed: 0 CoreFoundation 0x000000018ba4dde4 0x18b960000 + 974308 (__exceptionPreprocess + 164) 1 libobjc.A.dylib 0x000000018b512b60 0x18b4f8000 + 109408 (objc_exception_throw + 88) 2 CoreFoundation 0x000000018b97e69c 0x18b960000 + 124572 (-[__NSArrayM insertObject:atIndex:] + 1276) 3 Portrait 0x0000000257e16a94 0x257da3000 + 473748 (-[PTMSRResize addAdditionalOutput:] + 604) 4 Portrait 0x0000000257de91c0 0x257da3000 + 287168 (-[PTEffectRenderer initWithDescriptor:metalContext:useHighResNetwork:faceAttributesNetwork:humanDetections:prevTemporalState:asyncInitQueue:sharedResources:] + 6204) 5 Portrait 0x0000000257dab21c 0x257da3000 + 33308 (__33-[PTEffect updateEffectDelegate:]_block_invoke.241 + 164) 6 libdispatch.dylib 0x000000018b739b2c 0x18b738000 + 6956 (_dispatch_call_block_and_release + 32) 7 libdispatch.dylib 0x000000018b75385c 0x18b738000 + 112732 (_dispatch_client_callout + 16) 8 libdispatch.dylib 0x000000018b742350 0x18b738000 + 41808 (_dispatch_lane_serial_drain + 740) 9 libdispatch.dylib 0x000000018b742e2c 0x18b738000 + 44588 (_dispatch_lane_invoke + 388) 10 libdispatch.dylib 0x000000018b74d264 0x18b738000 + 86628 (_dispatch_root_queue_drain_deferred_wlh + 292) 11 libdispatch.dylib 0x000000018b74cae8 0x18b738000 + 84712 (_dispatch_workloop_worker_thread + 540) 12 libsystem_pthread.dylib 0x000000018b8ede64 0x18b8eb000 + 11876 (_pthread_wqthread + 292) 13 libsystem_pthread.dylib 0x000000018b8ecb74 0x18b8eb000 + 7028 (start_wqthread + 8)

I've spent way too long today trying to convert an Object Detection TensorFlow2 model to a CoreML object classifier (with bounding boxes, labels and probability score) The 'SSD MobileNet v2 320x320' is here: https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf2_detection_zoo.md And I've been following all sorts of posts and ChatGPT https://apple.github.io/coremltools/docs-guides/source/tensorflow-2.html#convert-a-tensorflow-concrete-function https://developer.apple.com/videos/play/wwdc2020/10153/?time=402 To convert it. I keep hitting the same errors though, mostly around: NotImplementedError: Expected model format: [SavedModel | concrete_function | tf.keras.Model | .h5 | GraphDef], got <ConcreteFunction signature_wrapper(input_tensor) at 0x366B87790> I've had varying success including missing output labels/predictions. But I simply want to create the CoreML model with all the right inputs and outputs (including correct names) as detailed in the docs here: https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/running_on_mobile_tf2.md It goes without saying I don't have much (any) experience with this stuff including Python so the whole thing's been a bit of a headache. If anyone is able to help that would be great. FWIW I'm not attached to any one specific model, but what I do need at minimum is a CoreML model that can detect objects (has to at least include lights and lamps) within a live video image, detecting where in the image the object is. The simplest script I have looks like this: import coremltools as ct import tensorflow as tf model = tf.saved_model.load("~/tf_models/ssd_mobilenet_v2_320x320_coco17_tpu-8/saved_model") concrete_func = model.signatures[tf.saved_model.DEFAULT_SERVING_SIGNATURE_DEF_KEY] mlmodel = ct.convert( concrete_func, source="tensorflow", inputs=[ct.TensorType(shape=(1, 320, 320, 3))] ) mlmodel.save("YourModel.mlpackage", save_format="mlpackage")

Greetings, Ive been exerimenting with the new Apple intelligence chat. I want to be able to use my custom LLM and I made that work (I can chat back and forward from the left panel with my server) but I cannot find out how to change the editor contents like chatgpt does. chatgpt is able to change the current editor and, seems like, all files in the pbx. I tried to catch the call with charles with no success. In the OpenIA platform docs it doesnt mention anything that could change the code shown. does anyone know how to achieve this? Is the apple intelliece documentation lacking this features and will it be completed soon? will this features even be open for developers?

May i know the bundle identifier for apple intelligence?

WWDC25: Combine Metal 4 machine learning and graphics Demonstrated a way to combine neural network in the graphics pipeline directly through the shaders, using an example of Texture Compression. However there is no mention of using which ML technique texture is compressed. Can anyone point me to some well known model/s for this particular use case shown in WWDC25.

I am using gemini2.5-flash with SwiftUI. How can I receive a response in JSON?

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?

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 ) } }

Recently, I'm trying to deploy some third-party LLM to Apple devices. The methodoloy is similar to https://github.com/Anemll/Anemll. The biggest issue I'm having now is the runtime memory usage. When there are multiple functions in a model (mlpackage or mlmodelc), the runtime memory usage for weights is somehow duplicated when I load all of them. Here's the detail: I created my multifunction mlpackage following https://apple.github.io/coremltools/docs-guides/source/multifunction-models.html I loaded each of the functions using the generated swift class: let config = MLModelConfiguration() config.computeUnits = MLComputeUnits.cpuAndNeuralEngine config.functionName = "infer_512"; let ffn1_infer_512 = try! mimo_FFN_PF_lut4_chunk_01of02(configuration: config) config.functionName = "infer_1024"; let ffn1_infer_1024 = try! mimo_FFN_PF_lut4_chunk_01of02(configuration: config) config.functionName = "infer_2048"; let ffn1_infer_2048 = try! mimo_FFN_PF_lut4_chunk_01of02(configuration: config) I observed that RAM usage increases linearly as I load each of the functions. Using instruments, I see that there are multiple HWX files generated and loaded, each of which contains all the weight data. My understanding of what's happening here: The CoreML framework did some MIL->MIL preprocessing before further compilation, which includes separating CPU workload from ANE workload. The ANE part of each function is moved into a separate MIL file then compile separately into a HWX file each. The problem is that the weight data of these HWX files are duplicated. Since that the weight data of LLMs is huge, it will cause out-of-memory issue on mobile devices. The improvement I'm hoping from Apple: I hope we can try to merge the processed MIL files back into one before calling ANECCompile(), so that the weights can be merged. I don't have control over that in user space and I'm not sure if that is feasible. So I'm asking for help here. Thanks.

Seeing this error from time to time: Context(debugDescription: "Content contains 4089 tokens, which exceeds the maximum allowed context size of 4096.", underlyingErrors: []) Of course, 4089 is less than 4096 so what is this telling me and how do I work around it? Is the limit actually lower than 4096?

Hi everyone, I'm working with VNFeaturePrintObservation in Swift to compute the similarity between images. The computeDistance function allows me to calculate the distance between two images, and I want to cluster similar images based on these distances. Current Approach Right now, I'm using a brute-force approach where I compare every image against every other image in the dataset. This results in an O(n^2) complexity, which quickly becomes a bottleneck. With 5000 images, it takes around 10 seconds to complete, which is too slow for my use case. Question Are there any efficient algorithms or data structures I can use to improve performance? If anyone has experience with optimizing feature vector clustering or has suggestions on how to scale this efficiently, I'd really appreciate your insights. Thanks!

I have an app that uses a couple of mlmodels (word tagger and gazetteer) and I’m trying to encrypt them before publishing. The models are part of a package. I understand that Xcode can’t automatically handle the encryption for a model in a package the way it can within a traditional app structure. Given that, I’ve generated the Apple MLModel encryption key from Xcode and am encrypting via the command line with: xcrun coremlcompiler compile Gazetteer.mlmodel GazetteerENC.mlmodelc --encrypt Gazetteerkey.mlmodelkey In the package manifest, I’ve listed the encrypted models as .copy resources for my target and have verified the URL to that file is good. When I try to load the encrypted .mlmodelc file (on a physical device) with the line:
 gazetteer = try NLGazetteer(contentsOf: gazetteerURL!) I get the error: Failed to open file: /…/Scanner.bundle/GazetteerENC.mlmodelc/coremldata.bin. It is not a valid .mlmodelc file. So my questions are: Does the NLGazetteer class support encrypted MLModel files? Given that my models are in a package, do I have the right general approach? Thanks for any help or thoughts.

I would like to make use of create ML to classify a motion. However, it seems it requires 2 classes at least to train or test it. What should I do as I only has 1 class (the target motion). Also, how to interpret the 'Recall' and 'F1 Score'

Hello, I have a question regarding hybrid execution for deep learning models on Apple's Neural Engine and CPU. I am aware that setting the precision of some layers to 32-bit allows hybrid execution across both the Neural Engine and the CPU. However, I would like to know if it is possible to achieve the same with 16-bit precision. Is there any specific configuration or workaround to enable hybrid execution in this case? Any guidance or documentation references would be greatly appreciated. Thank you!

I am running some experiments with WebGPU using the wgpu crate in rust. I have some Buffers already allocated in the GPU. Is it possible to use those already existing buffers directly as inputs to a predict call in CoreML? I want to prevent gpu to cpu download time as much as possible. Or are there any other ways to do something like this. Is this only possible using the latest Tensor object which came out with Metal 4 ?

While runninf Apple Foundation Model in iPhone simulator, I got this error: IPC error: Underlying connection interrupted What does this mean? Related to foundation model?

Here's the result: Very weird.

Hi team, We have implemented a writing tool inside a WebView that allows users to type content in a textarea. When the "Show Writing Tools" button is clicked, an AI-powered editor opens. After clicking the "Rewrite" button, the AI modifies the text. However, when clicking the "Replace" button, the rewritten text does not update the original textarea. Kindly check and help me showButton.addTarget(self, action: #selector(showWritingTools(_:)), for: .touchUpInside) @available(iOS 18.2, *) optional func showWritingTools(_ sender: Any) Note: same cases working in TextView pfa

Hello, I am interested in using jax-metal to train ML models using Apple Silicon. I understand this is experimental. After installing jax-metal according to https://developer.apple.com/metal/jax/, my python code fails with the following error JaxRuntimeError: UNKNOWN: -:0:0: error: unknown attribute code: 22 -:0:0: note: in bytecode version 6 produced by: StableHLO_v1.12.1 My issue is identical to the one reported here https://github.com/jax-ml/jax/issues/26968#issuecomment-2733120325, and is fixed by pinning to jax-metal 0.1.1., jax 0.5.0 and jaxlib 0.5.0. Thank you!

Hi everyone, I’m currently exploring the use of Foundation models on Apple platforms to build a chatbot-style assistant within an app. While the integration part is straightforward using the new FoundationModel APIs, I’m trying to figure out how to control the assistant’s responses more tightly — particularly: Ensuring the assistant adheres to a specific tone, context, or domain (e.g. hospitality, healthcare, etc.) Preventing hallucinations or unrelated outputs Constraining responses based on app-specific rules, structured data, or recent interactions I’ve experimented with prompt, systemMessage, and few-shot examples to steer outputs, but even with carefully generated prompts, the model occasionally produces incorrect or out-of-scope responses. Additionally, when using multiple tools, I'm unsure how best to structure the setup so the model can select the correct pathway/tool and respond appropriately. Is there a recommended approach to guiding the model's decision-making when several tools or structured contexts are involved? Looking forward to hearing your thoughts or being pointed toward related WWDC sessions, Apple docs, or sample projects.