Ollama

Ollama is an open-source tool for running open AI models such as Gemma, Llama, Qwen and DeepSeek locally on macOS, Windows and Linux. It downloads and runs models with one command and serves them through a local REST API.

Ollama makes local models easy: install it, run a model, and chat in the terminal or call it from your own code through its REST API and official Python and JavaScript libraries. It is also available as a Docker image, and it connects to coding agents and assistants such as OpenCode, OpenClaw and Claude Code.

Ollama is the standard way to run open models on your own hardware, which keeps your prompts and data on your machine. Many of the other AI tools in this collection support it out of the box, so it is often the first thing to install.

Stars

0

Forks

0

Commits

0

Repository

ollama/ollama

• LM StudioDesktop app for running local models, with a graphical interface but not open source.
• OpenAI APIOpenAI's hosted models, accessed over the internet and billed per token.
• LiteLLMNo. 091Open-source gateway that puts many model providers, including Ollama, behind one API.

See every open-source alternative to LM Studio in the collection.