Written by Jakub Rusinowski · Last updated July 12, 2026
Ollama is the easiest tool to get started with local LLMs. It packages the model weights, configuration, and a runtime engine into a single binary.
Ollama is the easiest tool to get started with local LLMs. It packages the model weights, configuration, and a runtime engine into a single binary.
1. Download Ollama for Windows. 2. Run the .exe installer. 3. Once installed, Ollama runs in the background (check your system tray).
1. Download Ollama for macOS. 2. Unzip the file and move Ollama to your Applications folder. 3. Open the application. You might need to approve it in 'Security & Privacy' settings if prompted.
Run the following command in your terminal:
curl -fsSL https://ollama.com/install.sh | shOllama works from the command line (Terminal on Mac/Linux, PowerShell/CMD on Windows).
To download and run the popular Llama 3.1 8B model, simply type:
ollama run llama3.1Ollama will: 1. Pull the model manifest. 2. Download the model layers (approx 4.7 GB). 3. Verify the hash. 4. Drop you into a chat prompt >>>.
You can now chat! Type 'Why is the sky blue?' and hit Enter.
| Command | Description |
|---|---|
ollama list | Show all models installed on your machine. |
ollama pull [model] | Download a model but don't run it immediately. |
ollama rm [model] | Remove a model to free up disk space. |
ollama serve | Start the Ollama background service manually. |
Ollama v0.32 is a major update for agentic workflows and Apple Silicon. The installer upgrades in place, so re-run it and confirm the version:
curl -fsSL https://ollama.com/install.sh | sh # macOS / Linux — upgrades in place
ollama --version # expect 0.32 or newerv0.32 adds an interactive agent mode: a tool-calling model can now plan, call tools, and chain steps in a loop directly from the CLI — no external agent framework required. Run a model that supports tool calling and hand it a task:
ollama run qwen3-coder:8bWith agent mode the model can invoke registered tools (shell commands, file read/write, web fetch) and keep iterating until the task is done. Everything runs on your machine, so source code and documents never leave it — the whole reason to run an agent locally instead of in the cloud. To wire up your own tools, see Building Autonomous Agents with Local LLMs.
Tool (function) calling is far more consistent in v0.32, and Ollama speaks the OpenAI-compatible tools format on its /v1/chat/completions endpoint — so existing OpenAI-SDK code works simply by pointing the base URL at http://localhost:11434/v1. Models with strong tool support today include Qwen3-Coder, Devstral-2, GLM-5, Kimi K2.x, and Llama 4. Structured JSON output (JSON-schema format) is steadier too — details in Reliable JSON From Local LLMs and Setting Up a Local API Server.
On M-series Macs, v0.32 can run supported models through an MLX backend (Apple's array framework) alongside the default llama.cpp engine. MLX uses the unified-memory architecture more directly and gives noticeably faster prompt processing and token generation on M3/M4 hardware. It engages automatically for supported models on Apple Silicon and falls back to the standard engine when a model isn't MLX-ready yet — nothing to configure. On Mac, keep an eye on memory: large models still need the unified RAM to hold the weights.
sudo systemctl start ollama).Now that you have Ollama running, check out the Model Library to find models to download.