Ollama: Chat with AI models on your own computer
Added · Updated
Made by Ollama
View profile on GitHub (opens in a new tab)Ollama lets you choose an AI model and chat with it on your own computer.
You can also connect it to a coding assistant or an app you are building.
What it does
Ollama is a program on your computer that downloads, starts, and manages AI models. You choose a model from its library or follow the model’s own instructions, then chat with it through Ollama. A coding assistant or an app you are building can use the same running model through a connection that sends questions and receives answers.
How to use it
Choose the installation route for your computer, install Ollama, and select a model from the library. Your input is a question or an app request; Ollama starts the selected model and returns an answer on your computer or through the connection used by your assistant or app.
Common use cases
- Chat with an AI model on your own computer when you want to run it there instead of using a hosted chat service.
- Connect a coding assistant such as Claude Code, OpenClaw, OpenCode, Codex, or Copilot to a model that Ollama serves.
- Give an app you are building a connection that lets it send questions to a model and receive answers.
Getting started
Reviewed setup route · source checked 2026-10-21 · Source page (opens in a new tab)
- Download the installer for macOS or Windows from the source’s Download section; Linux has a separate install route.
- Open a terminal and run the command ollama to be prompted to run a model.
- Or chat with a named model directly by running ollama run gemma4.
- Try with
- Run ollama run gemma4 and ask “Why is the sky blue?”, the source’s own example question.
- What to expect
- A chat reply from an open AI model; the source says models can run locally or in the cloud.
- Access note
- The source does not state hardware needs, model download sizes, or whether the cloud option needs an account.
Can I use this?
Requirements A supported macOS, Windows, Linux, or Docker installation; check the selected model’s own documentation for its requirements.
Caveat Hardware needs vary by model, so a model that works on one computer may not fit another.
Worth knowing Licensed under MIT.
Why it's here
Not trending this week
Last seen on the GitHub trending list on 3 November 2026. It stays on BuildTube so you can still find it.
- 186,337 people have starred it on GitHub.
Numbers checked on 8 November 2026; not refreshed since.
Behind it
View setup guideBuildTube has not run or verified this project. Everything above is written from what the creator published.
Made this?
Quick questions
- What is Ollama?
- Ollama is a program on your computer that downloads, starts, and manages AI models.
- What can I use Ollama for?
- Chat with an AI model on your own computer when you want to run it there instead of using a hosted chat service; Connect a coding assistant such as Claude Code, OpenClaw, OpenCode, Codex, or Copilot to a model that Ollama serves; Give an app you are building a connection that lets it send questions to a model and receive answers
- Can I run Ollama on my computer?
- It installs as a desktop app on your own computer. A supported macOS, Windows, Linux, or Docker installation; check the selected model’s own documentation for its requirements. Hardware needs vary by model, so a model that works on one computer may not fit another.
- What do I need to use Ollama?
- Choose a macOS, Windows, Linux, or Docker installation.
- What license does Ollama use?
- Licensed under MIT.
More from this week
- kimi-k3-in-c Run a 2.78-trillion-parameter model on 8 GB of RAM
Get text answers from the huge Kimi K3 AI model using one CPU and no graphics card.
- DS Harness Remote Reach your DeepSeek Harness from a phone or browser
Continue your DeepSeek Harness sessions from a phone, another computer or a browser while the work keeps running on your own machine.
- agent-desktop Let AI agents read and click desktop apps
For developers building computer-use agents: agent-desktop lets an AI agent read and operate desktop apps on Mac, Windows or Linux from a command line.
Explore by topic
Post this
Download share imageFor makers
Made this? Show it’s on BuildTube — add the badge to your README or embed the card on your site.
README badge (Markdown)
[](https://buildtube.app/p/gh-ollama-ollama/)Embed card (HTML)
<iframe src="https://buildtube.app/embed/gh-ollama-ollama/" width="560" height="240" style="border:0;max-width:100%" loading="lazy" title="Ollama on BuildTube"></iframe>