Give each workload its space
Assign GPUs to desktops, models and containers. Independent workloads load in parallel; a failure in one does not discard the others.
GPU workstations + local AI
A gaming desktop. A local model. Or both at once. Xur gives your GPUs a job, with profiles you control from a browser.
An image-based OS for GPU workload profiles, built on Bazzite.
Two desktops and a language model, each with its own GPUs.
A profile describes which workloads to run and where they belong. Save a few for the way you use your machine, then switch from the control panel.
Assign GPUs to desktops, models and containers. Independent workloads load in parallel; a failure in one does not discard the others.
Reuse a named workstation across profiles to keep its user and Moonlight pairing. Assign USB devices or a hub, and choose a primary desktop for shared peripherals.
Find ready language-model endpoints in one place. Try a conversation or retain a benchmark with the model, running workloads and sampled VRAM.
These example layouts use four RTX 3090s. Your profiles depend on the GPUs, memory and models you have.
Set up a workstation
Inside Xur
Choose a profile, manage desktops and see what is running. These screenshots show the real interface with example data. Select an image to view it full size.
Xur is MIT-licensed open source, with Nightly installers available. Follow development, inspect the code and report what works on your hardware. Download the installer or read the release notes on GitHub.
View releases