Skip to main content
Ollama logo

Ollama

Run LLMs locally

Run large language models locally. Get up and running with Llama, Mistral, and other open-source models with a simple CLI and API.

110.0k
GitHub Stars
free
Pricing
Yes
Self-Hostable

Features

  • Run LLMs locally
  • OpenAI-compatible API
  • Model library (Llama, Mistral, Gemma, etc.)
  • Custom model creation
  • GPU acceleration
  • REST API
  • Cross-platform (Mac, Linux, Windows)

Pros

  • + Completely free
  • + No API costs
  • + Data stays local
  • + Easy model switching
  • + Active development

Cons

  • Requires decent hardware
  • Limited to open-source models
  • No cloud fallback