Application
Inference & Serving
LocalAI
1A 2self-hosted, 3OpenAI-compatible 4local 5AI 6API.
the six Ws · specification
W1
Who
Open-source project by Ettore Di Giacinto.
W2
What
Serves local models behind an OpenAI-compatible API.
W3
Where
Runs on your own CPU or GPU hardware.
W4
When
When replacing OpenAI with local models.
W5
Why
Drop-in local alternative to hosted APIs.
W6
With
Local model files and a machine.