Compare software

KoboldCppOllama
Free

Free and open source under the AGPL.

 Freemium

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

Windows, macOS, Linux Windows, macOS, Linux, Command line
  • A single executable with no installation and no external dependencies
  • Runs on CPU or GPU, with partial offload for machines short on VRAM
  • 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
  • You still have to find and download model files yourself
  • Performance on CPU alone is slow for larger models
  • 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 Downloadable app
Open source Open source
License: AGPL-3.0 License: MIT
No account needed No account needed
Works offline Works offline

Checked September 21, 2026

Checked September 20, 2026

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