Ollama Local LLM Runner and Model Server
Ollama runs large language models locally with a simple CLI and REST API. It supports hundreds of open models including Llama, Gemma, Qwen, and DeepSeek, with GPU acceleration and an OpenAI-compatible API endpoint.
Installation
Use the upstream install or setup path that matches your environment:
- pip install ollama
- npm i ollama
Requirements and caveats from upstream:
Docker
- The official Ollama Docker image ollama/ollama is available on Docker Hub.
- ollama-python
Basic usage or getting-started notes:
You'll be prompted to run a model or connect Ollama to your existing agents or applications such as Claude Code, OpenClaw, OpenCode , Codex, Copilot, and more.
Run and chat with Gemma 3:
ollama run gemma3
Source: https://github.com/ollama/ollama
Extracted from upstream docs: https://raw.githubusercontent.com/ollama/ollama/HEAD/README.md
Source
Source: agentskillexchange/skills — distributed by TomeVault.