Running Models with Ollama

Ollama makes it easy to run open source LLMs locally on your machine.

#

Installation

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

#

Running Models

bash
ollama run llama2
ollama run mistral
ollama run codellama

#

API Integration

python
import requests
response = requests.post('http://localhost:11434/api/generate',
    json={"model": "llama2", "prompt": "Why is the sky blue?"})
print(response.json())

#

Benefits

Simple one-command model downloads

Automatic GPU acceleration

Built-in model management

REST API for easy integration