# Ollama

> Download and run open LLMs locally from your terminal

- Category: Models & Inference / Local Runtimes
- Language: Go
- Repository: https://github.com/ollama/ollama
- Website: https://ollama.com
- Canonical page: https://ai-tldr.dev/tools/ollama/
- Updated: 2026-09-14

## In short

Ollama is a tool for downloading and running open large language models on your own computer. You install it on macOS, Windows, or Linux, then pull and chat with a model straight from the terminal with a single command. It sits in the Local Runtimes category of the Models & Inference tools and is open-source, written in Go.

## Overview

Ollama is a tool for downloading and running open large language models on your own computer. You install it on macOS, Windows, or Linux, then pull and chat with a model straight from the terminal with a single command.

It is aimed at developers who want to run models locally instead of calling a hosted service. Beyond the CLI, Ollama exposes a REST API on localhost and ships official Python and JavaScript libraries, so you can wire local models into your own apps and scripts.

As a local runtime, Ollama handles model downloads, serving, and the request loop for you, and connects to existing coding tools and agents such as Claude Code, Codex, and Copilot CLI through its launch integrations.

## What it does

- One-line install script for macOS, Windows, and Linux, plus an official Docker image
- Run any model from the library with a single `ollama run` command
- Built-in REST API on http://localhost:11434 for running and managing models
- Official Python (`pip install ollama`) and JavaScript (`npm i ollama`) client libraries
- Launch integrations for coding tools and agents like Claude Code, Codex, and Copilot CLI
- Built on the llama.cpp backend for local model inference

## Getting started

Install Ollama, then pull and chat with a model from the terminal. The same models are reachable over a local REST API and the Python and JavaScript libraries.

1. Install Ollama

   Run the install script on macOS or Linux. On Windows, use the PowerShell command instead.

```bash
curl -fsSL https://ollama.com/install.sh | sh
```

2. Run and chat with a model

   Pull a model from the library and start chatting in the terminal.

```bash
ollama run gemma4
```

3. Call the REST API

   Ollama serves a local REST API on port 11434 for running models from your own apps.

```bash
curl http://localhost:11434/api/chat -d '{
  "model": "gemma4",
  "messages": [{
    "role": "user",
    "content": "Why is the sky blue?"
  }],
  "stream": false
}'
```

4. Use the Python library

   Install the official client and send a chat request from Python.

```python
pip install ollama

from ollama import chat

response = chat(model='gemma4', messages=[
  {
    'role': 'user',
    'content': 'Why is the sky blue?',
  },
])
print(response.message.content)
```

## When to use it

- Run open LLMs locally for privacy or offline work, without sending data to a hosted API
- Add a local model backend to a Python or JavaScript app through the official libraries
- Connect Ollama to coding tools and agents such as Claude Code, Codex, or Copilot CLI
- Prototype and test prompts against different models from the library before committing to a provider

## Version history

- 2026-09-14 v0.34.1: MLX safetensors support in ollama create is no longer experimental. Creating a GGUF model now requires llama.cpp tooling for safetensor conversion and quantization. The release also improves MLX memory handling on Apple Silicon, raises repeat-token detection to 100 tokens, and cuts the /api/tags cold load from 3.1 seconds to 294 milliseconds.
- 2026-09-05 v0.34.0-rc1: Ollama models can now be used directly in ChatGPT Desktop, with setup available from the Ollama app on macOS. The release also improves structured output performance on Apple Silicon and adds support for OpenAI-compatible client tool search and response compaction.