Install Ollama and Run LLMs Locally

Open a terminal and download a model. Start with Llama 3.2 (a great beginner model):

ollama pull llama3.2

This downloads ~2 GB. Other great free models:

ollama pull mistral          # Fast, 4 GB
ollama pull deepseek-coder   # Best for coding, 4 GB
ollama pull qwen2.5-coder    # Excellent coder, 4 GB
ollama pull phi3             # Small, fast, 2 GB

Once downloaded, run the model:

ollama run llama3.2

You'll see a prompt where you can start chatting:

>>> Hello! What can you help me with?

Type your message and press Enter. To exit, type /bye or press Ctrl + D.

For a nicer chat UI, install Open WebUI:

docker run -d -p 3000:8080 \
  --add-host=host.docker.internal:host-gateway \
  -v open-webui:/app/backend/data \
  --name open-webui \
  ghcr.io/open-webui/open-webui:main

Then open http://localhost:3000 in your browser for a ChatGPT-like interface connected to your local Ollama models.

Don't have Docker? You can also use Chatbox — a free desktop app that connects to Ollama.

See all downloaded models:

ollama list

Delete a model to free disk space:

ollama rm llama3.2

See what's running:

ollama ps

Browse all available models: Visit ollama.com/library — there are hundreds of models for coding, writing, math, and more.