Compare software

OllamaOpenLLM
Freemium

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

 Free

Free and open source under the Apache 2.0 licence; BentoCloud hosting is a separate…

Windows, macOS, Linux, Command line Self-hosted, Command line
  • 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
  • One command starts an OpenAI-compatible server
  • Wide catalogue of open models, plus custom model repositories
  • 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
  • Many models require large GPUs
  • Aimed at developers rather than desktop users
Downloadable app Downloadable app, Self-hosted
Open source Open source
License: MIT License: Apache-2.0
No account needed Not stated if an account is needed
Works offline Not stated if it works offline

Checked September 20, 2026

Checked September 26, 2026

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