AI0-001 AI Infrastructure and Technologies Practice Question
A company is deploying a computer vision model to smartphones for offline object detection. The model was trained in PyTorch. Which format should they use for deployment on iOS devices?
⚠ Common exam trap
AI0-001 often tests the confusion between cross-platform formats (ONNX, TorchScript) and platform-native formats (Core ML for iOS, TensorFlow Lite for Android) — candidates who pick ONNX for portability miss that iOS requires Core ML.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Core ML
Core ML is Apple's native machine learning framework for iOS, macOS, and other Apple platforms, and it requires models in the Core ML format (.mlmodel). Converting a PyTorch model to Core ML (via coremltools) enables on-device inference with optimized performance and integration with Apple's hardware accelerators.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
TorchScript
Why it's wrong here
TorchScript is PyTorch's intermediate representation for serialising and optimising models, but iOS deployment requires Core ML, which Xcode and Apple's runtime consume. TorchScript is tempting because it is the natural PyTorch export path, yet it targets the PyTorch runtime, not Apple's on-device inference framework.
- ✗
ONNX
Why it's wrong here
ONNX is an interchange format between training frameworks, not a mobile runtime; iOS cannot execute an ONNX graph directly. It suits moving models between frameworks or serving via ONNX Runtime on servers, not on-device inference on iPhone.
- ✓
Core ML
Why this is correct
Core ML is Apple's on-device inference framework, so converting the trained PyTorch model to Core ML format lets it run natively and offline on iOS hardware, using Neural Engine acceleration without a network connection or server round trip.
- ✗
TensorFlow Lite
Why it's wrong here
TensorFlow Lite targets Android and embedded devices through the TensorFlow ecosystem, requiring conversion from a TensorFlow or Keras model. It would be correct for an Android deployment, but an iOS app needs Core ML, and the stem specifies a PyTorch-trained model.
About these practice questions
One of 962 original AI0-001 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official CompTIA exam blueprint
This AI0-001 practice question is part of Courseiva's free CompTIA certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI0-001 exam.