ollama/ollama: Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Ollama is a platform for running open models locally, including Kimi-K2.6, GLM-5.1, DeepSeek, Qwen, Gemma, and others.
It provides one-line installer commands for macOS and Linux via curl and for Windows via PowerShell.
An official Ollama Docker image is available on Docker Hub.
Ollama can be used through integrations like Claude Code, Copilot, Codex, OpenCode, and others.
Users can launch OpenClaw to turn Ollama into a personal AI assistant across WhatsApp, Telegram, Slack, Discord, and more.
A model can be run directly from the CLI, for example with `ollama run gemma4`.
Ollama exposes a REST API for chatting with and managing models on localhost port 11434.
Official client libraries are provided for Python and JavaScript.
Ollama is built on the llama.cpp backend project founded by Georgi Gerganov.
The page lists a large ecosystem of community integrations, including chat interfaces, code editors, SDKs, agents, RAG tools, bots, CLI tools, and productivity apps.

Your notes

Save this item to your library to add private notes.