M
All Guides

Running Local AI Models with Ollama

Run local AI models on your computer using Ollama. LLama, Mistral, Gemma and more.

Intermediate20 min

Setup Steps

1. Install Ollama on Linux:

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

2. For macOS:

brew install ollama

3. Start the Ollama service:

ollama serve

4. Download and run a model (e.g., Llama 3.1):

ollama run llama3.1

5. Other popular models:

ollama run mistral
ollama run gemma2
ollama run codellama
ollama run phi3

6. List installed models:

ollama list

7. API usage:

curl http://localhost:11434/api/generate -d '{
  "model": "llama3.1",
  "prompt": "Hello!"
}'

8. Python usage:

pip install ollama
python
import ollama
response = ollama.chat(model='llama3.1', messages=[{'role': 'user', 'content': 'Hello!'}])
print(response['message']['content'])

Related Guides

Claude Code Setup

Install Anthropic Claude Code CLI on your server or PC. API key configuration and basic commands.

ChatGPT API Setup

Integrate OpenAI ChatGPT API into your project. Getting API keys and sending your first request.

Google Gemini API Setup

Set up Google Gemini (formerly Bard) API and use it in your projects.

Midjourney Usage Guide

Create AI-powered images with Midjourney. Step-by-step guide for Discord usage.