TECHNOLOGY PROFILE · TECH-0040
Core ML
Apple framework for integrating models into native applications.
Reference link only — not reviewed this edition. This profile preserves the prepared catalog’s original descriptions. Advantages depend on the workload; comparisons are editorial, not benchmark results.
Where it has an edge
Uses Apple hardware and system integration without shipping an independent inference service.
Best-fit problems
On-device models in iOS and macOS applications.
Tradeoffs & cautions
Apple-platform lock-in and conversion/operator constraints.
What to test before choosing
Test the actual target device offline; measure load time, memory, battery/thermal behavior and task accuracy.
Runtime & hardware
Local device; supported CPU/GPU/NPU
Access & licensing
Mixed licenses; check model and app terms
Execution
Local / self-hosted
Lifecycle
Not independently audited
Comparison basis
Editorial problem-fit judgement; no head-to-head benchmark performed
Connected concepts
Alternatives to investigate
ExecuTorch · LiteRT · MLX