Get started
Running in minutes.
Install LocalAI, run a model, then open it in your browser.
Install it
Use the script on Linux and on a Mac with Apple Silicon, a container on any platform, or the macOS app.
shellScript
$ curl -sSL https://localai.io/install.sh | sh $ local-ai run qwen3-4b # the API and the web UI are on http://localhost:8080
Docker
$ docker run -p 8080:8080 --name local-ai -ti localai/localai:latest # Podman works the same way
Kubernetes
$ helm repo add go-skynet https://go-skynet.github.io/helm-charts/ $ helm install local-ai go-skynet/local-ai # or: kubectl apply -f https://localai.io/install/kubernetes.yaml
More: containers and GPU images, the macOS app, Linux, Helm chart, build from source
The script, the macOS app and the latest container image give version 4.12.1. Office, Sandbox, Team and add-ons need a development build or a newer release.
Run a model
This downloads the model from the gallery and starts it. The first run also downloads the engine the model needs.
local-ai run qwen3-4bOpen it
Go to
http://localhost:8080in your browser and start a chat. The API is on the same address.Add more
Ask an admin to install add-ons such as Office or Sandbox, and to turn on the features your team needs.
In development builds, coming in the next release.