Getting Started with Ollama
Ollama makes it easy to run open-weight AI models locally on your machine. Follow this guide to get up and running in minutes.
1. Install Ollama
macOS
Download from the official website or install via Homebrew:
brew install ollama
Linux
Use the official install script:
curl -fsSL https://ollama.com/install.sh | sh
Windows
Download the installer from ollama.com/download and run the setup wizard.
2. Run Your First Model
Once installed, you can run a model with a single command. Let's start with Llama 3.2 3B — a small, fast model that runs on virtually any modern hardware:
ollama run llama3.2:3b
Ollama will automatically download the model (about 2GB) and start a chat session. Type your message and press Enter to chat.
3. Try Other Models
Here are some popular models to try, roughly ordered by VRAM requirements:
| Command | Model | Min VRAM | Best For |
|---|---|---|---|
| ollama run llama3.2:1b | Llama 3.2 1B | ~2 GB | Quick tasks, low-end hardware |
| ollama run llama3.2:3b | Llama 3.2 3B | ~3 GB | Good starting point |
| ollama run llama3.1:8b | Llama 3.1 8B | ~6 GB | Great all-rounder |
| ollama run qwen2.5-coder:7b | Qwen 2.5 Coder 7B | ~6 GB | Code generation |
| ollama run deepseek-r1:14b | DeepSeek R1 14B | ~10 GB | Reasoning, math |
| ollama run llama3.3:70b | Llama 3.3 70B | ~43 GB | Best open-weight quality |
4. Check Your Hardware
Not sure what your hardware can run? Use our compatibility checker:
Check Compatibility →Useful Commands
ollama list List all downloaded models
ollama pull llama3.1:8b Download a model without starting a chat
ollama rm llama3.1:8b Delete a downloaded model to free space
ollama serve Start the Ollama API server (runs on port 11434)