Skip to main content

Ollama Installation

Ollama is a powerful local large language model (LLM) framework that enables users to efficiently run various open-source large language models on their own computers.

Ollama Features​

  • Cross-Platform Support

    Supports macOS, Linux, and Windows operating systems, meeting the needs of different user groups.

  • User-Friendly

    Provides a clean command-line interface that makes downloading, running, and managing large language models extremely convenient.

  • Extensive Model Support

    Supports running various open-source large language models, including popular ones like DeepSeek, Qwen, and LLama.

  • Local Execution

    All models run locally, ensuring data privacy and security without relying on cloud services.

  • High Performance

    Optimized for local environments, making full use of hardware resources to provide a smooth interactive experience.

  • Developer-Friendly

    Offers API interfaces, making it easy for developers to integrate models into their own applications.

Installing Ollama​

You can install Ollama using the official Linux installation script.

Open a terminal and run the following command to download and execute the installation script:

radxa@device$
curl -fsSL https://ollama.com/install.sh | sh

The terminal will display the installation progress and information. Upon successful installation, you'll see output similar to the following:

> > > Installing ollama to /usr/local
> > > Downloading Linux arm64 bundle
> > > ######################################################################## 100.0%
> > > Creating ollama user...
> > > Adding ollama user to render group...
> > > Adding ollama user to video group...
> > > Adding current user to ollama group...
> > > Creating ollama systemd service...
> > > Enabling and starting ollama service...
> > > Created symlink /etc/systemd/system/default.target.wants/ollama.service → /etc/systemd/system/ollama.service.
> > > The Ollama API is now available at 127.0.0.1:11434.
> > > Install complete. Run "ollama" from the command line.
> > > WARNING: No NVIDIA/AMD GPU detected. Ollama will run in CPU-only mode.

Verifying Ollama Installation​

You can check the Ollama version information using the ollama -v command.

radxa@device$
ollama -v

If the Ollama version number is displayed successfully, the installation was successful.