Skip to main content
Contact Us
EDGE AI · SOFTWARE

What Is OpenVINO?

OpenVINO is Intel's open-source toolkit for optimizing and running AI inference. It takes models trained in frameworks such as PyTorch, TensorFlow or ONNX, optimizes them, and runs them efficiently on Intel hardware, including CPUs, integrated GPUs such as Iris Xe and Arc, and the NPUs in Core Ultra processors.

01

The Short Answer

OpenVINO matters at the edge because it lets an ordinary Intel processor do useful AI work without a separate accelerator. It can compress models, for example to 8-bit integers, and split work across the CPU, GPU and NPU on the same chip, which keeps cost, power and heat down in compact embedded systems.

  • //
    Converts models Imports trained models from common frameworks.
  • //
    Optimizes them Quantisation and graph optimization for faster inference.
  • //
    Targets the hardware Runs on the CPU, iGPU or NPU, or a mix.
  • //
    Deploys at scale The same model runs across a range of Intel-based edge devices.
02

Why It Matters

Our iGPU vs dGPU FAQ explains when integrated graphics are enough, and our inference vs training FAQ covers the workload. The COM Express reverse vending case study runs OpenVINO on Iris Xe graphics.