Ollama
BuildersLocal modelsOllama
Run open-weight models locally with a simple CLI and API.
- Who it's for: people building software and AI agents
- Pricing: Free, open source (verify on the official site)
- Official site: https://ollama.com
- Source / changelog: https://github.com/ollama/ollama
Best for / Not for
Best for
- Running open models privately on your own machine
- Development without API costs
- Offline or sensitive workloads
Not for
- Tasks needing frontier-level reasoning
- Low-RAM machines
3 concrete use cases
- Private summaries: Summarize confidential notes locally with a Modelfile-based summarizer.
- OpenAI-compatible dev: Point OpenAI SDK code at http://localhost:11434/v1/.
- Local classifier: Use a small model to tag emails in a self-hosted n8n workflow.
Pros and cons
Pros
- Free and open source
- One-command model downloads
- OpenAI-compatible endpoint
Cons
- Quality limited by model size and hardware
- Default context is 4,096 tokens
- No built-in auth if exposed on a network
How to get started with Ollama in 10 minutes
- Install with the script from ollama.com
- Run ollama run gemma4 (or another library model)
- Chat; type /bye to exit
- Call http://localhost:11434/api/chat from curl
- Read our Ollama playbook
Playbooks using Ollama
Recent changes
Weekly updates for Ollama will be logged here as they appear in issues.