Apache 2.0 on-device runtime for machine learning and generative AI, the successor to TensorFlow Lite.
LiteRT is Google AI Edge's runtime for deploying models on phones, embedded devices and other edge platforms, providing model conversion, an efficient runtime and optimisation tooling. It was renamed from TensorFlow Lite in September 2024; TFLite packages still work, but new development targets LiteRT.
Phone, embedded device or single-board computer
Specifications taken from current manufacturer documentation and last checked on 2026-09-08.
Source: manufacturer documentation
Specifications are summarised from publicly published manufacturer material and are provided for orientation only. Always confirm current figures directly with the manufacturer before purchasing or designing in.
Client processor platform with an NPU rated up to 48 TOPS alongside an Intel Arc Xe2 GPU and hybrid CPU cores.
Arm-based 4 nm PC platform with twelve Oryon CPU cores, Adreno graphics and a Hexagon NPU for on-device AI.
Apache 2.0 compact vision-language model family, from 2 billion parameters down to a 256 million variant.