Application
Inference & ServingApps & UIs
text-generation-webui
1Gradio 2web 3UI 4for 5local 6LLMs
the six Ws · specification
W1
Who
Maintained by oobabooga and contributors.
W2
What
A Gradio-based web UI for running and chatting with local LLMs across many backends.
W3
Where
Runs self-hosted as a Python app on CPU or GPU, cross-platform.
W4
When
Reach for it when you want a flexible local playground for many model formats.
W5
Why
Broad backend support and extensions make it a hub for local experimentation.
W6
With
Model weights and appropriate loaders; GPU recommended for larger models.
W7
Watch
Community open-source (AGPL-3.0); self-hostable and runs fully offline for privacy.