TFLite LiteRT TensorFlow Test vs Vision Detector

How fast does your .tflite model actually run on this iPhone? Pick CPU, GPU or Neural Engine. Get real latency and QPS. No Mac, no Xcode project, no Bazel build, no cloud, no account. Open a .tflite file from the Files app, pick an accelerator, run it. A real measurement on the exact device you care about, in about a minute — no Bazel workspace, no benchmark tool built from source. PICK THE ACCELERATOR - Neural Engine — attaches the Core ML delegate, so supported operators run on the Apple Neural Engine - GPU — attaches the GPU delegate, backed by Metal - CPU — the plain interpreter, with a thread count you choose: 1, 2, 4, 6 or 8 One configuration per run: run it, change the delegate or thread count, load it again, compare the numbers yourself. WHAT YOU GET - Latency: mean, min and max, in milliseconds - Queries per second - Total queries completed and total run duration - A query count you set per run, from 50 to 5,000 invocations Mean, min and max time the model inference call only — no pre-processing, no post-processing. Duration covers the whole loop. The screen stays awake during a run. WHAT YOU SEE ABOUT THE MODEL - Every input and output tensor: index, name, shape and data type (uInt8, int32, float16, float32 and the rest) - Model file size and framework - Live app memory usage against the memory available to the app, refreshed while the model runs - A device tab with model identifier, system version, disk space, and the exact TensorFlow Lite runtime version this build links against A MobileNet model ships in the app and loads on launch, so you see a real measurement before importing your own. READ THIS BEFORE YOU TRUST A NUMBER Inference runs on a zeroed dummy input. The app fills every input tensor with zeros and invokes the model, so what you measure is the compute cost of the graph on the accelerator you picked — latency and throughput, nothing else. It is not an accuracy test. It will not tell you whether your model gives the correct answer, and it does not show output tensor values. Ask it "how fast", not "how correct". What it does not do, stated up front: no side-by-side accelerator comparison in one run, no per-layer or per-operator profiling, no result export, no image or real-data input. It opens .tflite files only. PRIVACY Your model never leaves the device. Loading, inspection, inference and timing all happen locally on your iPhone or iPad. No account, no sign-in — your models and your results are never uploaded. TensorFlow Lite is now called LiteRT; the format and the .tflite extension are unchanged. TensorFlow, the TensorFlow logo and any related marks are trademarks of Google Inc. Not affiliated with or endorsed by Google.

Vision Detector is an AI image analysis tool that supports CoreML machine learning models, multi-modal Large Language Models, and on-device Apple Intelligence. Choose the mode that best fits your use case. You can choose one of the following image input sources: - Live video by built-in camera - Still image by the built-in camera - Photo Library - Files (iCloud, Google Drive, Dropbox, etc) For live video inputs, continuous inference is performed on the camera feed. However, the frame rate and other parameters depend on the device. # Notification Center Vision Detector can call Notification Center for predefined conditions. Broadcasting notifications send notification to your all Apple devices signed in with the same Apple Account. ## CoreML Mode Vision Detector locally executes CoreML models using Apple’s Vision framework. Before using this mode, prepare a machine learning model in the CoreML format (.mlmodel or .mlpackage) using Create ML. Import ML models via iClpoud or AirDrop. Vision Detector supports the following types of CoreML models: - Image classification - Object detection - Style transfer ## Vision LLM Mode Vision Detector can use multi-modal large language model (LLMs). Define what to do with prompt as following samples: - If the image is screen shot, answer the name software - Call notification when you see a cat - Count number of persons in the image, and notify when it changes ## Apple Intelligence mode Available with iOS 27 on selected devices (iPhone 17 Pro, iPhone Air, etc). The images are completely processed on your device locally with your prompt.