OpenVINO™ toolkit: An open source AI toolkit that makes it easier to write once, deploy anywhere.
System Requirements
Disclaimer. Certain hardware (including but not limited to GPUs, Gausian Network Accelerators (GNA), and the latest CPUs) requires manual installation of specific drivers and other software components to work correctly and to use hardware capabilities at their best. This might require updates to your operating system, including but not limited to the Linux* kernel. (For details, refer to the the Linux kernel documentation.) These modifications should be handled by the user and are not part of an OpenVINO installation.
Development Platforms
Processors
- 6th to 13th generation Intel® Core™ processors
- Intel® Core™ Ultra processor
- 1st to 4th generation Intel® Xeon® Scalable processors
- Arm* and Arm64 CPUs
- Apple* M1 and M2
- Raspberry Pi*
Compatible Operating Systems
- Ubuntu* 22.04 long-term support (LTS), 64 bit (Kernel 5.15+)
- Ubuntu 20.04 LTS, 64 bit (Kernel 5.15+)
- Ubuntu 18.04 LTS with limitations, 64 bit (Kernel 5.4+)
- Windows® 10 and 11
- macOS* 10.15 and later, 64 bit
- macOS* 11 and later, Arm64
- Red Hat* Enterprise Linux* 8, 64 bit
- Debian* 9, Arm64, and Arm
- CentOS* 7 64-bit
Note
To support a CPU, GPU, Intel® Gaussian & Neural Accelerator (Intel® GNA), or a hybrid core with CPU capabilities, newer versions of the Ubuntu operating system kernel may be required for:
- 10th and 11th generation Intel Core processors
- 11th generation Intel Core processors S-series
- 12th and 13th generation Intel Core processors
- 4th generation Intel Xeon Scalable processors
Target System Platforms
CPU
Processors
- 6th to 13th generation Intel Core processors
- 1st to 4th generation of Intel Xeon Scalable processors
- Intel® Pentium® processor N4200/5, N3350/5, N3450/5 with Intel® HD Graphics
- Intel Atom® processor with Intel® Streaming SIMD Extensions 4.2 (Intel® SSE4.2)
Compatible Operating Systems
- Ubuntu 18.04 LTS (64 bit)
- Ubuntu 20.04 LTS (64 bit)
- Ubuntu 22.04 LTS (64 bit)
- Windows 10
- Windows 11
- Red Hat Enterprise Linux 8 (64 bit)
- macOS 10.15 (64 bit)
GPU
Processors
- Intel® Processor Graphics with corresponding operating systems (GEN Graphics)
- Intel® HD Graphics
- Intel® UHD Graphics
- Intel® Iris® Pro Graphics
- Intel® Iris® Xe Graphics
- Intel® Iris® Xe MAX Graphics
For more information, see the installation guides.
Discrete Graphics
- Intel® Data GPU Flex Series Center
- Intel Data Center GPU Max Series
- Intel® Arc™ GPU
Compatible Operating Systems
- Ubuntu 20.04 LTS (64 bit)
- Ubuntu 22.04 LTS (64 bit)
- Windows 10 (64 bit)
- Windows 11 (64 bit)
- CentOS 7
- Red Hat Enterprise Linux 8 (64 bit)
Neural Processing Unit from Intel
Compatible operating systems:
- Ubuntu 22.04 LTS, 64-bit
- Windows 11, 64-bit
Notes
- This installation requires drivers that are not included in the Intel® Distribution of OpenVINO™ toolkit package.
- A chipset that supports processor graphics is required for Intel Xeon processors. Processor graphics are not included in all processors. For more information about your processor, see Product Specifications.
- While this release of the OpenVINO toolkit supports Ubuntu 20.04, the driver stack for discrete graphic cards from Intel does not fully support Ubuntu 20.04. It is recommended to use Ubuntu 22.04 when running on discrete graphics.
- For older hardware, the following minimum OpenCL™ Driver versions were used during OpenVINO internal validation: 22.43 for Ubuntu 22.04, 21.48 for Ubuntu 20.04, and 21.49 for Red Hat Enterprise Linux* 8.
Intel® Gaussian & Neural Accelerator (Intel® GNA)
Supported Hardware
- Intel GNA
Compatible Operating Systems
- Ubuntu 22.04 LTS (64 bit)
- Ubuntu 20.04 LTS (64 bit)
- Windows 10 (64 bit)
- Windows 11 (64 bit)
Additional Software Requirements
A Linux environment needs these components:
- Ubuntu 22.04 with Linux kernel 5.15+
- Ubuntu 20.04 with Linux kernel 5.15+
- Red Hat Enterprise Linux 8 with Linux kernel 5.4
A Linux build environment needs these components:
- Python* 3.8-3.11
- Intel® HD Graphics Driver: Required for inference on GPUs.
Note: GNU* Compiler Collection and CMake* are needed for building from source:- GNU Compiler Collection (GCC) 7.5 or higher
- CMake 3.10 or higher
- To support CPU, GPU, GNA, or hybrid-cores CPU capabilities, higher versions of the kernel might be required for:
- 10th generation Intel Core processors
- 11th generation Intel Core processors
- 11th generation Intel Core processor S-Series
- 12th generation Intel Core processors
- 13th generation Intel Core processors
- 14th generation Intel Core processors
- Intel Core Ultra processors
- 4th generation Intel Xeon Scalable processors
- 5th generation Intel Xeon Scalable processors
A Windows environment needs these components:
- Microsoft Visual Studio* 2019
- CMake 3.10 or higher (64 bit)
- Python 3.8-3.11
- Intel® HD Graphics Driver (Required only for GPUs.)
A macOS environment needs these components:
- CMake 3.10 or higher
- Xcode* 10.3
- Python 3.8-3.11
Deep learning framework versions:
- TensorFlow* 1.15, 2.12
- Apache MxNet* 1.9.0
- ONNX* (Open Neural Network Exchange) 1.14.1
- PaddlePaddle* 2.4
Notes
This package can be installed on other versions of DL Framework but only the specified version above are fully validated.
OpenVINO toolkit with Python binaries and binaries on Windows, CentOS 7, macOS (x86) are built with Intel® oneAPI Threading Building Blocks (oneTBB) libraries. Others on Ubuntu and RedHat* operating systems are built with legacy Intel® Threading Building Blocks (Intel® TBB), which is released by operating system distribution. OpenVINO supports being built with oneTBB or legacy Intel TBB from source on all of the previously listed operating systems. System compatibility and performance were improved on hybrid CPUs like 12th generation Intel Core processors and later.
Sign Up for Exclusive News, Tips & Releases
Be among the first to learn about everything new with the Intel® Distribution of OpenVINO™ toolkit. By signing up, you get early access product updates and releases, exclusive invitations to webinars and events, training and tutorial resources, contest announcements, and other breaking news.
Resources
Community and Support
Explore ways to get involved and stay up-to-date with the latest announcements.
Get Started
Optimize, fine-tune, and run comprehensive AI inference using the included model optimizer and runtime and development tools.