Compare software

Xinference vs llama-swap: catalog facts
Xinference	llama-swap
Free Free and open source.	Free Free and open source under the MIT licence.
macOS, Linux, Self-hosted, Command line	Self-hosted, Command line
Serves language, speech and multimodal models from one place API designed as a drop-in replacement for GPT calls	One binary and one config file with no dependencies Works with any OpenAI or Anthropic compatible backend
Aimed at developers rather than casual users Requires setup and suitable hardware for larger models	Requires writing a YAML configuration by hand Does not run models itself; you still need the backend servers
Downloadable app, Self-hosted	Downloadable app, Self-hosted
Open source	Open source
License not stated	License: MIT
Not stated if an account is needed	No account needed
Not stated if it works offline	Works offline
Official website Full listing and sources Checked September 23, 2026	Official website Full listing and sources Checked September 26, 2026

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