Ollama

A command-line tool for locally running and managing open-source large language models

No screenshots available

Download Ollama

Download Ollamaunknown · .dmg · 180.2 MB

macOS package (.dmg), architecture unlisted — verify before installing

Other downloads (2)

ollama-darwin.tgz
unknown · .tar.gz · 146.8 MB
Download
Ollama-darwin.zip
unknown · .zip · 179.6 MB
Download

Getting a "can't verify the developer" warning?

If you see a warning on first launch, go to System Settings > Privacy & Security and click "Open Anyway". Open source software usually isn't signed with an Apple developer certificate, which is normal.

Clicking "Download" takes you to a source confirmation page first; the download starts after confirmation.

About Ollama

Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

See incorrect information? Tell us

Who it's for

Individuals who want to run and try out open-source large language models directly on their local computer
Developers who need to integrate large models into their own applications (via REST API or SDK)
Researchers or teams who value data privacy and prefer models to run locally
AI enthusiasts who want to quickly download and switch between different models from the command line

Who it's not for

Users lacking high-performance local hardware (e.g., large RAM, dedicated GPU), as the experience may be limited
Users who prefer a purely graphical interface and are not comfortable with the command line
Production users who require enterprise-grade hosting and technical support

Install guide

macOS

Download the installer: This site recommends Ollama.dmg.
Open Ollama.dmg and drag the Ollama icon into the Applications folder.
On first launch, if the system warns that the app cannot be opened because the developer is unidentified, right-click the app icon and select "Open," or click "Open Anyway" in "System Settings → Privacy & Security."
Alternatively, install via the command line: run curl -fsSL https://ollama.com/install.sh | sh in Terminal.

Windows

Download the installer: This site recommends OllamaSetup.exe.
Double-click to run the installer and follow the prompts.
After installation, verify by running ollama in Command Prompt or PowerShell.
You can also install online by running irm https://ollama.com/install.ps1 | iex in PowerShell.

Other installer notes

For manual installation or a portable version, download ollama-windows-amd64.zip (64-bit) or ollama-windows-arm64.zip (ARM devices), unzip, and run ollama.exe.
On macOS, you can also download Ollama-darwin.zip and unzip it for use.
Linux users can download the ollama-linux-*.tar.zst file for their architecture and install manually following the official documentation.
After installation, you can start using models with ollama run gemma4 (gemma4 is an example model in the README).

FAQ

Is Ollama free?

Yes. Ollama itself is open source under the MIT license and free to use. However, models downloaded through Ollama have their own licenses, so please check each model's licensing before use.

Which operating systems are supported?

Officially supports macOS, Windows, and Linux, and also provides a Docker image. This site provides the main installation files for macOS and Windows.

How do I update Ollama to the latest version?

The easiest way is to download the latest installer from the official website or this site and reinstall over the existing version. You can also update using the official install script or a package manager such as Homebrew.

How do I get started after installation?

Run `ollama` in Terminal or Command Prompt to see help, and run `ollama run gemma4` to download and start a conversation. See the official quickstart guide for detailed commands.