TECHNOLOGY PROFILE · TECH-0145
LiteRT
Google on-device inference runtime, formerly TensorFlow Lite.
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
Mobile and embedded execution with supported delegates fits compact on-device models.
Best-fit problems
Android and embedded applications with supported model conversions.
Tradeoffs & cautions
Operator/delegate support and conversion correctness vary by target.
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 · Core ML · ONNX Runtime