Hi all, I’m encountering an issue when trying to run Apple Foundation Models in a blank project targeting iOS 26. Below are the details: Xcode: Latest version with iOS 26 SDK macOS: macOS 26 Tahoe (installed on main disk) Mac: 16” MacBook Pro with M2 Pro chip Apple Intelligence: Available and functional on this machine Problem: I created a new blank iOS project, set the deployment target to iOS 26, and ran the following minimal code using Foundation Models. However, I get no response at all in the output - not even an error. The app runs, but the model does not produce any output. #Playground { let session = LanguageModelSession() let response = try await session.respond(to: "Tell me a story") } Then, I tried to catch an error with this code: #Playground { let session = LanguageModelSession() do { let response = try await session.respond(to: "Tell me a story") print(response) } catch { print("Failed to get response:", error) } print("This line, never gets executed") } And got these results: I’ve done further testing and discovered something important: I tried running the Code Along sample project, and there the #Playground macro worked without issues. The only significant difference I noticed was the Canvas run destination: In my original project, I was using iPhone 16 Pro (iOS 26) as the run target in Canvas. Apple Intelligence was enabled on the simulator, but no response was returned when executing the prompt. In the sample project, the Canvas was running on My Mac. I attempted to match that setup, but at first, my destination was My Mac (Designed for iPad), which still didn’t work. The macro finally executed properly once I switched to My Mac (AppKit). So the question is ... it seems that for now, Foundation Models and the #Playground macro only run correctly when the canvas or destination is set to “My Mac (AppKit)”?

Hello, I'm unable to develop for Apple Intelligence on my Mac Studio, M1 Max running macOS 26 beta 1. The models get downloaded and I can also verify that they exist in /System/Library/AssetsV2/ however the download progress remains stuck at 100%. Checking console logs shows the process generativeexperiencesd reporting the following: My device region and language is set to English (India). Things I've already tried: Changing language and region to English (US) Reinstalling macOS Trying with a different ISP via hotspot.

After updating to macOS15.2beta, the Yolo11 object detection model exported to coreml outputs incorrect and abnormal bounding boxes. It also doesn't work in iOS apps built on a 15.2 mac. The same model worked fine on macOS14.1. When training a Yolo11 custom model in Python, exporting it to coreml, and testing it in the preview tab of mlpackage on macOS15.2 and Xcode16.0, the above result is obtained.

Hi, unfortunately I am not able to verify this but I remember some time ago I was able to create CoreML models that had one (or more) inputs with an enumerated shape size, and one (or more) inputs with a static shape. This was some months ago. Since then I updated my MacOS to Sequoia 15.5, and when I try to execute MLModels with this setup I get the following error libc++abi: terminating due to uncaught exception of type CoreML::MLNeuralNetworkUtilities::AsymmetricalEnumeratedShapesException: A model doesn't allow input features with enumerated flexibility to have unequal number of enumerated shapes, but input feature global_write_indices has 1 enumerated shapes and input feature input_hidden_states has 3 enumerated shapes. It may make sense (but not really though) to verify that for inputs with a flexible enumerated shape they all have the same number of possible shapes is the same, but this should not impede the possibility of also having static shape inputs with a single shape defined alongside the flexible shape inputs.

Hi all. My adapter model just won't invoke my tool. The problem I am having is covered in an older post: https://developer.apple.com/forums/thread/794839?answerId=852262022#852262022 Sadly the thread dies there and no resolution is seen in that thread. It's worth noting that I have developed an AI chatbot built around LanguageModelSession to which I feed the exact same system prompt that I feed to my training set (pasted further in this post). The AI chatbot works perfectly, the tool is invoked when needed. I am training the adapter model because the base model whilst capable doesn't produce the quality I'm looking for. So here's the template of an item in my training set: [ { 'role': 'system', 'content': systemPrompt, 'tools': [TOOL_DEFINITION] }, { 'role': 'user', 'content': entry['prompt'] }, { 'role': 'assistant', 'content': entry['code'] } ] where TOOL_DEFINITION = { 'type': 'function', 'function': { 'name': 'WriteUbersichtWidgetToFileSystem', 'description': 'Writes an Übersicht Widget to the file system. Call this tool as the last step in processing a prompt that generates a widget.', 'parameters': { 'type': 'object', 'properties': { 'jsxContent': { 'type': 'string', 'description': 'Complete JSX code for an Übersicht widget. This should include all required exports: command, refreshFrequency, render, and className. The JSX should be a complete, valid Übersicht widget file.' } }, 'required': ['jsxContent'] } } ... and systemPrompt = A conversation between a user and a helpful assistant. You are an Übersicht widget designer. Create Übersicht widgets when requested by the user. IMPORTANT: You have access to a tool called WriteUbersichtWidgetToFileSystem. When asked to create a widget, you MUST call this tool. ### Tool Usage: Call WriteUbersichtWidgetToFileSystem with complete JSX code that implements the Übersicht Widget API. Generate custom JSX based on the user's specific request - do not copy the example below. ### Übersicht Widget API (REQUIRED): Every Übersicht widget MUST export these 4 items: - export const command: The bash command to execute (string) - export const refreshFrequency: Refresh rate in milliseconds (number) - export const render: React component function that receives {output} prop (function) - export const className: CSS positioning for absolute placement (string) Example format (customize for each request): WriteUbersichtWidgetToFileSystem({jsxContent: `export const command = "echo hello"; export const refreshFrequency = 1000; export const render = ({output}) => { return <div>{output}</div>; }; export const className = "top: 20px; left: 20px;"`}) ### Rules: - The terms "ubersicht widget", "widget", "a widget", "the widget" must all be interpreted as "Übersicht widget" - Generate complete, valid JSX code that follows the Übersicht widget API - When you generate a widget, don't just show JSON or code - you MUST call the WriteUbersichtWidgetToFileSystem tool - Report the results to the user after calling the tool ### Examples: - "Generate a Übersicht widget" → Use WriteUbersichtWidgetToFileSystem tool - "Can you add a widget that shows the time" → Use WriteUbersichtWidgetToFileSystem tool - "Create a widget with a button" → Use WriteUbersichtWidgetToFileSystem tool When the script that I use to compose the full training set is executed, entry['prompt'] and entry['code'] contain the prompt and the resulting JSX code for one of the examples I'm feeding to the training session. This is repeated for about 60 such examples that I have in my sample data collection. Thanks for any help. Michael

Also submitted as feedback (ID: FB20612561). Tensorflow-metal fails on tensorflow versions above 2.18.1, but works fine on tensorflow 2.18.1 In a new python 3.12 virtual environment: pip install tensorflow pip install tensor flow-metal python -c "import tensorflow as tf" Prints error: Traceback (most recent call last): File "", line 1, in File "/Users//pt/venv/lib/python3.12/site-packages/tensorflow/init.py", line 438, in _ll.load_library(_plugin_dir) File "/Users//pt/venv/lib/python3.12/site-packages/tensorflow/python/framework/load_library.py", line 151, in load_library py_tf.TF_LoadLibrary(lib) tensorflow.python.framework.errors_impl.NotFoundError: dlopen(/Users//pt/venv/lib/python3.12/site-packages/tensorflow-plugins/libmetal_plugin.dylib, 0x0006): Library not loaded: @rpath/_pywrap_tensorflow_internal.so Referenced from: <8B62586B-B082-3113-93AB-FD766A9960AE> /Users//pt/venv/lib/python3.12/site-packages/tensorflow-plugins/libmetal_plugin.dylib Reason: tried: '/Users//pt/venv/lib/python3.12/site-packages/tensorflow-plugins/../_solib_darwin_arm64/_U@local_Uconfig_Utf_S_S_C_Upywrap_Utensorflow_Uinternal___Uexternal_Slocal_Uconfig_Utf/_pywrap_tensorflow_internal.so' (no such file), '/Users//pt/venv/lib/python3.12/site-packages/tensorflow-plugins/../_solib_darwin_arm64/_U@local_Uconfig_Utf_S_S_C_Upywrap_Utensorflow_Uinternal___Uexternal_Slocal_Uconfig_Utf/_pywrap_tensorflow_internal.so' (no such file), '/opt/homebrew/lib/_pywrap_tensorflow_internal.so' (no such file), '/System/Volumes/Preboot/Cryptexes/OS/opt/homebrew/lib/_pywrap_tensorflow_internal.so' (no such file)

Dear Apple Foundation Models Development Team, I am a developer integrating Apple Foundation Models (AFM) into my app and encountered the exceededContextWindowSize error when exceeding the 4096-token limit. Proposal: I suggest Apple develop a tool to estimate the token count of a prompt before sending it to the model. This tool could be integrated into FoundationModels Framework for ease of use. Benefits: A token estimation tool would help developers manage the context window limit and optimize performance. I hope Apple considers this proposal soon. Thank you!

Not finding a lot on the Swift Assist technology announced at WWDC 2024. Does anyone know the latest status? Also, currently I use OpenAI's macOS app and its 'Work With...' functionality to assist with Xcode development, and this is okay, certainly saves copying code back and forth, but it seems like AI should be able to do a lot more to help with Xcode app development. I guess I'm looking at what people are doing with AI in Visual Studio, Cline, Cursor and other IDEs and tools like those and feel a bit left out working in Xcode. Please let me know if there are AI tools or techniques out there you use to help with your Xcode projects. Thanks in advance!

Did something change on face detection / Vision Framework on iOS 15? Using VNDetectFaceLandmarksRequest and reading the VNFaceLandmarkRegion2D to detect eyes is not working on iOS 15 as it did before. I am running the exact same code on an iOS 14 and iOS 15 device and the coordinates are different as seen on the screenshot? Any Ideas?

Hey, I receive GenerableContent as follows: let response = try await session.respond(to: "", schema: generationSchema) And it wraps GeneratedJSON which seems to be private. What is the best way to get a string / raw value out of it? I noticed it could theoretically be accessed via transcriptEntries but it's not ideal.

Hi, I was using Foundation Models in my app, and suddenly it just stopped working from one moment to the next. To double-check, I created a small test in Playgrounds, but I’m getting the exact same error there too. #Playground { let session = LanguageModelSession() let prompt = "please answer a word" do { let response = try await session.respond(to: prompt) } catch { print("error is \(error)") } } error is Error Domain=FoundationModels.LanguageModelSession.GenerationError Code=-1 "(null)" UserInfo={NSMultipleUnderlyingErrorsKey=( "Error Domain=ModelManagerServices.ModelManagerError Code=1026 \"(null)\" UserInfo={NSMultipleUnderlyingErrorsKey=(\n)}" )} I’m no longer able to get any response from the framework anywhere, even in a fresh project. It's been 5 days. Has anyone else experienced this issue or knows what could be causing it? Thanks in advance! Tahoe 26.2 beta 1, Xcode 26.1.1, iPhone Air simulator 26.1

We’ve encountered what appears to be a CoreML regression between macOS 26.0.1 and macOS 26.1 Beta. In macOS 26.0.1, CoreML models run and produce correct results. However, in macOS 26.1 Beta, the same models produce scrambled or corrupted outputs, suggesting that tensor memory is being read or written incorrectly. The behavior is consistent with a low-level stride or pointer arithmetic issue — for example, using 16-bit strides on 32-bit data or other mismatches in tensor layout handling. Reproduction Install ON1 Photo RAW 2026 or ON1 Resize 2026 on macOS 26.0.1. Use the newest Highest Quality resize model, which is Stable Diffusion–based and runs through CoreML. Observe correct, high-quality results. Upgrade to macOS 26.1 Beta and run the same operation again. The output becomes visually scrambled or corrupted. We are also seeing similar issues with another Stable Diffusion UNet model that previously worked correctly on macOS 26.0.1. This suggests the regression may affect multiple diffusion-style architectures, likely due to a change in CoreML’s tensor stride, layout computation, or memory alignment between these versions. Notes The affected models are exported using standard CoreML conversion pipelines. No custom operators or third-party CoreML runtime layers are used. The issue reproduces consistently across multiple machines. It would be helpful to know if there were changes to CoreML’s tensor layout, precision handling, or MLCompute backend between macOS 26.0.1 and 26.1 Beta, or if this is a known regression in the current beta.

I'm experimenting with downloading an audio file of spoken content, using the Speech framework to transcribe it, then using FoundationModels to clean up the formatting to add paragraph breaks and such. I have this code to do that cleanup: private func cleanupText(_ text: String) async throws -> String? { print("Cleaning up text of length \(text.count)...") let session = LanguageModelSession(instructions: "The content you read is a transcription of a speech. Separate it into paragraphs by adding newlines. Do not modify the content - only add newlines.") let response = try await session.respond(to: .init(text), generating: String.self) return response.content } The content length is about 29,000 characters. And I get this error: InferenceError::inferenceFailed::Failed to run inference: Context length of 4096 was exceeded during singleExtend.. Is 4096 a reference to a max input length? Or is this a bug? This is running on an M1 iPad Air, with iPadOS 26 Seed 1.

Has anyone been able to run Tensorflow > 2.15 with Tensorflow Metal 1.1.0 on M3? I tried several times but was not successful. Seems like development on TensorFlow Metal has paused?

When I try to run visionOS 26 beta 2 on my device the app crashes on Launch: dyld[904]: Symbol not found: _$s16FoundationModels10TranscriptV7entriesACSayAC5EntryOG_tcfC Referenced from: <A71932DD-53EB-39E2-9733-32E9D961D186> /private/var/containers/Bundle/Application/53866099-99B1-4BBD-8C94-CD022646EB5D/VisionPets.app/VisionPets.debug.dylib Expected in: <F68A7984-6B48-3958-A48D-E9F541868C62> /System/Library/Frameworks/FoundationModels.framework/FoundationModels Symbol not found: _$s16FoundationModels10TranscriptV7entriesACSayAC5EntryOG_tcfC Referenced from: <A71932DD-53EB-39E2-9733-32E9D961D186> /private/var/containers/Bundle/Application/53866099-99B1-4BBD-8C94-CD022646EB5D/VisionPets.app/VisionPets.debug.dylib Expected in: <F68A7984-6B48-3958-A48D-E9F541868C62> /System/Library/Frameworks/FoundationModels.framework/FoundationModels dyld config: DYLD_LIBRARY_PATH=/usr/lib/system/introspection DYLD_INSERT_LIBRARIES=/usr/lib/libLogRedirect.dylib:/usr/lib/libBacktraceRecording.dylib:/usr/lib/libMainThreadChecker.dylib:/usr/lib/libViewDebuggerSupport.dylib:/System/Library/PrivateFrameworks/GPUToolsCapture.framework/GPUToolsCapture Symbol not found: _$s16FoundationModels10TranscriptV7entriesACSayAC5EntryOG_tcfC Referenced from: <A71932DD-53EB-39E2-9733-32E9D961D186> /private/var/containers/Bundle/Application/53866099-99B1-4BBD-8C94-CD022646EB5D/VisionPets.app/VisionPets.debug.dylib Expected in: <F68A7984-6B48-3958-A48D-E9F541868C62> /System/Library/Frameworks/FoundationModels.framework/FoundationModels dyld config: DYLD_LIBRARY_PATH=/usr/lib/system/introspection DYLD_INSERT_LIBRARIES=/usr/lib/libLogRedirect.dylib:/usr/lib/libBacktraceRecording.dylib:/usr/lib/libMainThreadChecker.dylib:/usr/lib/libViewDebuggerSupport.dylib:/System/Library/PrivateFrameworks/GPUToolsCapture.framework/GPUToolsCapture Message from debugger: Terminated due to signal 6

Using Tensorflow for Silicon gives inaccurate results when compared to Google Colab GPU (9-15% differences). Here are my install versions for 4 anaconda env's. I understand the Floating point precision can be an issue, batch size, activation functions but how do you rectify this issue for the past 3 years? 1.) Version TF: 2.12.0, Python 3.10.13, tensorflow-deps: 2.9.0, tensorflow-metal: 1.2.0, h5py: 3.6.0, keras: 2.12.0 2.) Version TF: 2.19.0, Python 3.11.0, tensorflow-metal: 1.2.0, h5py: 3.13.0, keras: 3.9.2, jax: 0.6.0, jax-metal: 0.1.1,jaxlib: 0.6.0, ml_dtypes: 0.5.1 3.) python: 3.10.13,tensorflow: 2.19.0,tensorflow-metal: 1.2.0, h5py: 3.13.0, keras: 3.9.2, ml_dtypes: 0.5.1 4.) Version TF: 2.16.2, tensorflow-deps:2.9.0,Python: 3.10.16, tensorflow-macos 2.16.2, tensorflow-metal: 1.2.0, h5py:3.13.0, keras: 3.9.2, ml_dtypes: 0.3.2 Install of Each ENV with common example: Create ENV: conda create --name TF_Env_V2 --no-default-packages start env: source TF_Env_Name ENV_1.) conda install -c apple tensorflow-deps , conda install tensorflow,pip install tensorflow-metal,conda install ipykernel ENV_2.) conda install pip python==3.11, pip install tensorflow,pip install tensorflow-metal,conda install ipykernel ENV_3) conda install pip python 3.10.13,pip install tensorflow, pip install tensorflow-metal,conda install ipykernel ENV_4) conda install -c apple tensorflow-deps, pip install tensorflow-macos, pip install tensor-metal, conda install ipykernel Example used on all 4 env: import tensorflow as tf cifar = tf.keras.datasets.cifar100 (x_train, y_train), (x_test, y_test) = cifar.load_data() model = tf.keras.applications.ResNet50( include_top=True, weights=None, input_shape=(32, 32, 3), classes=100,) loss_fn = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False) model.compile(optimizer="adam", loss=loss_fn, metrics=["accuracy"]) model.fit(x_train, y_train, epochs=5, batch_size=64)

Testing Foundation Models framework with a health-focused recipe generation app. The on-device approach is appealing but performance is rough. Taking 20+ seconds just to get recipe name and description. Same content from Claude API: 4 seconds. I know it's beta and on-device has different tradeoffs, but this is approaching unusable territory for real-time user experience. The streaming helps psychologically but doesn't mask the underlying latency.The privacy/cost benefits are compelling but not if users abandon the feature before it completes. Anyone else seeing similar performance? Is this expected for beta, or are there optimization techniques I'm missing?

Here's the result: Very weird.

In working with Apple's foundation models, we often want to provide as much context as possible. However, since the model has a context size limit of 4096 tokens, is there a way to estimate the number of tokens beforehand?

I am working on an app using FoundationModels to process web pages. I am looking to find ways to filter the input to fit within the token limits. I have unit tests, UI tests and the app running on an iPad in the simulator. It appears that the different configurations of the test environment seems to affect the token limits. That is, the same input in a unit test and UI test will hit different token limits. Is this correct? Or is this an artifact of my test tooling?