Compare software

TabbyAPIOllama
Free

Free and open source.

 Freemium

Running models locally is free. The optional hosted cloud inference starts at $20 a month.

Windows, Linux, Self-hosted, Command line Windows, macOS, Linux, Command line
  • OpenAI-compatible endpoints for existing clients
  • Lightweight server focused on ExLlama models
  • One command to download and run a model, with no Python environment to build first
  • A REST API on localhost, so editors, scripts and agents can use the local model
  • Only serves ExLlama-format models
  • No built-in chat interface; pair it with a separate front end
  • Model quality is bounded by your hardware; large models need a lot of VRAM or unified memory
  • The company now also sells cloud inference, so read carefully which mode you are in
Downloadable app, Self-hosted Downloadable app
Open source Open source
License not stated License: MIT
No account needed No account needed
Works offline Works offline

Checked September 23, 2026

Checked September 20, 2026

Catalog facts only. Anything “not stated” is unconfirmed. Check full listings for details.