Ollama

Overview

Ollama is a tool for downloading open models and running them locally or in the cloud. With a single command, you can chat with a model or connect Ollama to the coding agents and applications you already use.

It provides install scripts for macOS, Windows and Linux as well as a Docker image, and uses llama.cpp as its internal backend. It has a REST API for running and managing models, plus Python and JavaScript libraries, so you can call it directly from your own programs. The ollama launch command also integrates it with coding tools such as Claude Code and Codex.

It suits developers and practitioners who want to work with open models directly in their own environment. The official site states that it does not store users' prompts or use them for training.

What it is used for

• Download open models to your computer and chat with them.
• Connect a coding agent to an Ollama model.
• Call models from an app through the REST API or the Python and JavaScript libraries.
• Connect it to OpenClaw to build a personal AI assistant you use in a messaging app.

Pricing and license

See the official site

Getting started

1. On macOS and Linux, run curl -fsSL https://ollama.com/install.sh | sh .
2. On Windows, run irm https://ollama.com/install.ps1 | iex or download the installer.
3. Run ollama to choose a model or connect it to existing tools.
4. Enter a model name, as in ollama run gemma4 , to start chatting right away.

Links

Official site ↗Repository ↗

Related terms and companies

Local LLM Open weights Inference Inference engine LLM Ollama

Recent mentions in briefings

• Ollama v0.40.4 RC adds decision models and EmbeddingGemma 2, shows local models in Codex model picker 2026-10-14
• Apple researchers release 'Minions,' which pools idle Mac GPUs for distributed ML inference (community reports) 2026-10-14
• AWS publishes guide to deploying decision models on SageMaker AI with llama.cpp, using SemIf to return per-option probabilities 2026-10-13
• Ollama v0.40.0 makes the MLX runtime the default on Apple Silicon 2026-10-07

Sources

• ollama/ollama README
• Ollama · Run AI models locally and in the cloud

Compiled from public sources (official pages, READMEs). Pricing and features change, so check the official site.