Overview
Ollama makes running large language models locally simple and accessible. With just a few commands, you can run Llama 3, Mistral, CodeLlama, and many other models.
Key Features
- Simple CLI: One-command model execution
- Model Library: Extensive model collection
- Cross-platform: macOS, Linux, Windows
- API Server: REST API built-in
- Custom Models: Import your own
Installation
# macOS / Linux
curl -fsSL https://ollama.com/install.sh | sh
# Run a model
ollama run llama3
Popular Models
| Model | Parameters | Use Case |
|---|---|---|
| llama3 | 8B | General purpose |
| mistral | 7B | Fast, efficient |
| codellama | 7B | Code generation |
| phi3 | 3.8B | Lightweight |
| gemma | 7B | Google open model |
Resources
Source: GitHub