Install OpenVINO™ Runtime on Linux from an Archive File — OpenVINO™ documentation (original) (raw)
Note
Note that the Archive distribution:
- offers both C/C++ and Python APIs
- additionally includes code samples
- is dedicated to Linux users (archives for other systems are also available)
- may offer different hardware support under different operating systems (see the drop-down below for more details).
| Operating System | CPU | GPU | NPU |
|---|---|---|---|
| Debian9 armhf | V | n/a | n/a |
| Ubuntu20 arm64 | V | n/a | n/a |
| CentOS7 x86_64 | V | V | n/a |
| Ubuntu20 x86_64 | V | V | V |
| Ubuntu22 x86_64 | V | V | V |
| RHEL8 x86_64 | V | V | n/a |
Before installing OpenVINO, see theSystem Requirements page.
Installing OpenVINO Runtime#
Step 1: Download and Install the OpenVINO Core Components#
- Open a command prompt terminal window. You can use the keyboard shortcut: Ctrl+Alt+T
- Create the
/opt/intelfolder for OpenVINO by using the following command. If the folder already exists, skip this step.
Note
The/opt/intelpath is the recommended folder path for administrators or root users. If you prefer to install OpenVINO in regular userspace, the recommended path is/home/<USER>/intel. You may use a different path if desired. - Browse to the current user’s
Downloadsfolder: - Download the OpenVINO Runtime archive file for your system, extract the files, rename the extracted folder and move it to the desired path:
x86_64
Ubuntu 24.04
curl -L https://storage.openvinotoolkit.org/repositories/openvino/packages/2025.4/linux/openvino_toolkit_ubuntu24_2025.4.0.20398.8fdad55727d_x86_64.tgz --output openvino_2025.4.0.tgz
tar -xf openvino_2025.4.0.tgz
sudo mv openvino_toolkit_ubuntu24_2025.4.0.20398.8fdad55727d_x86_64 /opt/intel/openvino_2025.4.0
Ubuntu 22.04
curl -L https://storage.openvinotoolkit.org/repositories/openvino/packages/2025.4/linux/openvino_toolkit_ubuntu22_2025.4.0.20398.8fdad55727d_x86_64.tgz --output openvino_2025.4.0.tgz
tar -xf openvino_2025.4.0.tgz
sudo mv openvino_toolkit_ubuntu22_2025.4.0.20398.8fdad55727d_x86_64 /opt/intel/openvino_2025.4.0
Ubuntu 20.04
curl -L https://storage.openvinotoolkit.org/repositories/openvino/packages/2025.4/linux/openvino_toolkit_ubuntu20_2025.4.0.20398.8fdad55727d_x86_64.tgz --output openvino_2025.4.0.tgz
tar -xf openvino_2025.4.0.tgz
sudo mv openvino_toolkit_ubuntu20_2025.4.0.20398.8fdad55727d_x86_64 /opt/intel/openvino_2025.4.0
RHEL 8
curl -L https://storage.openvinotoolkit.org/repositories/openvino/packages/2025.4/linux/openvino_toolkit_rhel8_2025.4.0.20398.8fdad55727d_x86_64.tgz --output openvino_2025.4.0.tgz
tar -xf openvino_2025.4.0.tgz
sudo mv openvino_toolkit_rhel8_2025.4.0.20398.8fdad55727d_x86_64 /opt/intel/openvino_2025.4.0
CentOS 7
curl -L https://storage.openvinotoolkit.org/repositories/openvino/packages/2025.4/linux/openvino_toolkit_centos7_2025.4.0.20398.8fdad55727d_x86_64.tgz --output openvino_2025.4.0.tgz
tar -xf openvino_2025.4.0.tgz
sudo mv openvino_toolkit_centos7_2025.4.0.20398.8fdad55727d_x86_64 /opt/intel/openvino_2025.4.0
ARM 64-bit
curl -L https://storage.openvinotoolkit.org/repositories/openvino/packages/2025.4/linux/openvino_toolkit_ubuntu20_2025.4.0.20398.8fdad55727d_arm64.tgz -O openvino_2025.4.0.tgz
tar -xf openvino_2025.4.0.tgz
sudo mv openvino_toolkit_ubuntu20_2025.4.0.20398.8fdad55727d_arm64 /opt/intel/openvino_2025.4.0
ARM 32-bit
curl -L https://storage.openvinotoolkit.org/repositories/openvino/packages/2025.4/linux/openvino_toolkit_debian10_2025.4.0.20398.8fdad55727d_armhf.tgz -O openvino_2025.4.0.tgz
tar -xf openvino_2025.4.0.tgz
sudo mv openvino_toolkit_debian10_2025.4.0.20398.8fdad55727d_armhf /opt/intel/openvino_2025.4.0 - Install required system dependencies on Linux. To do this, OpenVINO provides a script in the extracted installation directory. Run the following command:
cd /opt/intel/openvino_2025.4.0
sudo -E ./install_dependencies/install_openvino_dependencies.sh - (Optional) Install numpy Python Library:
Note
This step is required only when you decide to use Python API.
You can use therequirements.txtfile from the/opt/intel/openvino_2025.4.0/pythonfolder:
cd /opt/intel/openvino_2025.4.0
python3 -m pip install -r ./python/requirements.txt - For simplicity, it is useful to create a symbolic link as below:
cd /opt/intel
sudo ln -s openvino_2025.4.0 openvino_2025
Note
If you have already installed a previous release of OpenVINO 2025, a symbolic link to theopenvino_2025folder may already exist. Unlink the previous link withsudo unlink openvino_2025, and then re-run the command above.
Congratulations, you have finished the installation! For some use cases you may still need to install additional components. Check the description below, as well as thelist of additional configurationsto see if your case needs any of them.
The /opt/intel/openvino_2025 folder now contains the core components for OpenVINO. If you used a different path in Step 2, for example, /home/<USER>/intel/, OpenVINO is now in /home/<USER>/intel/openvino_2025. The path to the openvino_2025directory is also referred as <INSTALL_DIR> throughout the OpenVINO documentation.
Step 2: Configure the Environment#
You must update several environment variables before you can compile and run OpenVINO applications. Open a terminal window and run the setupvars.sh script as shown below to temporarily set your environment variables. If your <INSTALL_DIR> is not /opt/intel/openvino_2025, use the correct one instead.
source /opt/intel/openvino_2025/setupvars.sh
If you have more than one OpenVINO version installed on your system, you can easily switch versions by sourcing the setupvars.sh of your choice.
Note
The above command must be re-run every time you start a new terminal session. To set up Linux to automatically run the command every time a new terminal is opened, open ~/.bashrc in your favorite editor and add source /opt/intel/openvino_2025/setupvars.sh after the last line. Next time when you open a terminal, you will see [setupvars.sh] OpenVINO™ environment initialized. Changing .bashrc is not recommended when you have multiple OpenVINO versions on your machine and want to switch among them.
The environment variables are set.
What’s Next?#
Now that you’ve installed OpenVINO Runtime, you’re ready to run your own machine learning applications! Learn more about how to integrate a model in OpenVINO applications by trying out the following tutorials.
Uninstalling the Intel® Distribution of OpenVINO™ Toolkit#
If you have installed OpenVINO Runtime from archive files, you can uninstall it by deleting the archive files and the extracted folders. Uninstallation removes all Intel® Distribution of OpenVINO™ Toolkit component files but does not affect user files in the installation directory.
If you have created the symbolic link, remove the link first:
sudo rm /opt/intel/openvino_2025
To delete the files:
rm -r && rm
Additional Resources#
- Troubleshooting Guide for OpenVINO Installation & Configuration
- Converting models for use with OpenVINO™: Convert a Model
- Writing your own OpenVINO™ applications: OpenVINO™ Runtime User Guide
- Sample applications: OpenVINO™ Toolkit Samples Overview
- Pre-trained deep learning models on Hugging Face.