Compare software

llama.cppKoboldCpp
Free

Free and open source under the MIT licence.

 Free

Free and open source under the AGPL.

Windows, macOS, Linux, Android, Command line Windows, macOS, Linux
  • No Python and no dependencies; one binary runs the model
  • Quantisation down to 1.5 bits fits big models into small memory
  • A single executable with no installation and no external dependencies
  • Runs on CPU or GPU, with partial offload for machines short on VRAM
  • Command line first; the web interface is basic next to dedicated apps
  • Quantising hard reduces answer quality, and the trade-off is yours to judge
  • You still have to find and download model files yourself
  • Performance on CPU alone is slow for larger models
Downloadable app Downloadable app
Open source Open source
License: MIT License: AGPL-3.0
No account needed No account needed
Works offline Works offline

Checked September 21, 2026

Checked September 21, 2026

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