LiteRT
GoogleLiteRT is Google's on-device runtime for machine learning and generative AI, and the successor to TensorFlow Lite. It runs converted PyTorch, TensorFlow and JAX models on Android, iOS, the web, desktop and IoT devices, choosing a CPU, GPU or NPU accelerator automatically, with NPUs from Google Tensor, Qualcomm, MediaTek, Intel and others behind one API. LiteRT-LM, which runs language models on device, is built on it.
TensorFlow Lite was renamed LiteRT, and the .tflite model format carries over. LiteRT-LM, the language-model layer built on this runtime, is its own product on the map.
Openness
5 high confidence- license
- Apache-2.0 (OSI)
- source
- public
- core features withheld
- no
LiteRT is Apache-2.0 licensed, and the repository holds the runtime, its accelerator layers and the guide for building an NPU backend outside it. A chipmaker's own NPU SDK, such as Qualcomm's, carries that vendor's terms, but nothing in LiteRT itself is gated.
- https://pypi.org/pypi/ai-edge-litert/json recorded 2026-11-12
PyPI metadata for ai-edge-litert 2.3.0 carries the classifier "License :: OSI Approved :: Apache Software License".
- https://raw.githubusercontent.com/google-ai-edge/LiteRT/main/LICENSE recorded 2026-11-12
The LICENSE file is the Apache License text, "Version 2.0, January 2004".
- https://raw.githubusercontent.com/google-ai-edge/LiteRT/main/README.md recorded 2026-11-12
The README states "LiteRT is licensed under the Apache-2.0 License" and links a "Build Your Own NPU Backend" guide; no paid tier or gated feature is described.
Adoption
3 medium confidencePyPI downloads of the two Python packages, ai-edge-litert and tflite-runtime, the TensorFlow Lite runtime package it replaced, which still sees heavy use. Android apps, LiteRT's main audience, take it from Google's Maven repository, and Maven publishes no download count, so the Android channel is left out and this is a floor on use.
- https://pypi.org/pypi/tflite-runtime/json recorded 2026-11-12
PyPI metadata for tflite-runtime 2.14.0: summary "TensorFlow Lite is for mobile and embedded devices.", homepage tensorflow.org/lite, the same summary and homepage ai-edge-litert carries; last upload 2023-10-03.
- https://pypistats.org/api/packages/ai-edge-litert/recent recorded 2026-11-12
"last_month":467037 downloads for ai-edge-litert.
- https://pypistats.org/api/packages/tflite-runtime/recent recorded 2026-11-12
"last_month":330766 downloads for tflite-runtime.
Capability
4 medium confidenceLiteRT sits a tier below vLLM, level with ExecuTorch, its closest peer: both run converted models on phone, desktop and embedded silicon, and LiteRT's single NPU API covers a comparable spread of chip vendors. It runs models on a device rather than serving them with batching, parallelism and a multi-tenant API.
- https://raw.githubusercontent.com/google-ai-edge/LiteRT/main/README.md recorded 2026-11-12
The README lists the "Compiled Model API" with "automated accelerator selection" and "true asynchronous execution", "Unified NPU Acceleration", "GPU Acceleration via ML Drift", CPU via XNNPack, and a platform table covering Android (Broadcom, Google Tensor, Intel, MediaTek, Qualcomm, S.LSI NPUs), iOS, Linux, macOS, Windows, Web and IoT.
Verified 2026-11-12