OpenVINO Runtime
Run compatible vision, language, and other neural networks on local Intel hardware.
Published by Intel
How to use it
Use the OpenVINO Runtime API to read a supported model and compile it for a chosen device. OpenVINO IR uses an XML graph and a separate binary weights file. Supported ONNX models can also be loaded through the frontend.
Measure correctness and latency on the CPU first, then compare available GPU or NPU devices. Driver and model compatibility differ by operating system, device, and model operators.
- Hardware
- CPU, Intel GPU, Intel NPU
- Model formats
- OpenVINO IR, ONNX
- Operating systems
- Linux, Windows
- Access
- Runs locally. Install the runtime and drivers appropriate to the device.