DEDUPEDWhat do you want to do?
3 use cases
-
Run an open model on your machine in one command
Install Ollama and chat with a model like Gemma from the terminal.
- REPO
ollama/ollama - Software and DevOps
- Beginner
View prompt
Install ollama/ollama, run `ollama run gemma4`, and ask <question>. Confirm the answer was generated locally.
- REPO
-
Call a local model from Python or JavaScript
Use the REST API on port 11434 or the official libraries in your app.
- REPO
ollama/ollama - Software and DevOps
- Intermediate
View prompt
Using the ollama Python library, send <prompt> to gemma4 and print the reply. Confirm the request went to localhost:11434.
- REPO
-
Launch a coding agent backed by Ollama
Use Ollama launch to start tools like Claude Code configured for Ollama models.
View prompt
Run `ollama launch claude` and complete <small coding task> using an Ollama model. Report which model was used.
Quick start with Ollama
- Check you have what it needs: macOS, Windows, Linux or Docker; Enough RAM or VRAM for the model you pick.
- Open ollama/ollama on GitHub and read the README and license.
- Install with
curl -fsSL https://ollama.com/install.sh | sh(orirm https://ollama.com/install.ps1 | iexon Windows) - Run
ollama run gemma4 - Chat in the terminal
- Try other models from the library
These steps come from our top use case, Run an open model on your machine in one command, which also has a copy-paste agent prompt.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for ollama/ollama
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeAbout this repo
- Who it is forDevelopers and tinkerers who want to run open models on their own machine and call them from code.
- Why it is hot184k stars
- LanguageGo
- Sourcegithub.com/ollama/ollama · Back to Hot repos
Requirements
- macOS, Windows, Linux or Docker
- Enough RAM or VRAM for the model you pick
Add this badge to your README
Maintain Ollama? Show readers where to find these use cases. 
Markdown
[](https://dedupedai.com/use-cases/ollama-ollama/?utm_source=github&utm_medium=badge&utm_campaign=ollama-ollama)
HTML
<a href="https://dedupedai.com/use-cases/ollama-ollama/?utm_source=github&utm_medium=badge&utm_campaign=ollama-ollama"><img src="https://dedupedai.com/badge/ollama/ollama.svg" alt="Use cases on Deduped" height="20"></a>
A static image, no tracking script. About the badge
Questions about Ollama
What is Ollama?
Ollama runs open models such as Gemma, Qwen, DeepSeek, Kimi and gpt-oss locally or in the cloud, with a CLI, a local REST API and official Python and JavaScript libraries. It is an open-source project on GitHub: https://github.com/ollama/ollama.
Who is Ollama for?
Developers and tinkerers who want to run open models on their own machine and call them from code.
What can I do with Ollama?
3 use cases so far, for example: Run an open model on your machine in one command; Call a local model from Python or JavaScript; Launch a coding agent backed by Ollama. Each has steps and a copy-paste agent prompt.
What do I need to run Ollama?
macOS, Windows, Linux or Docker; Enough RAM or VRAM for the model you pick.
What are alternatives to Ollama?
Other hot AI repos in Software and DevOps: Deep Infer, Harness2, Orca, Opencode, Graphify.
Is Ollama safe to run?
Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.