
Runs your AI in your building
Models run on your own cards, so questions and documents never leave the building.
The AI and inference role: runs your models and your everyday apps.


Models run on your own cards, so questions and documents never leave the building.

We size the machine for the models you want to run, on graphics cards you own.

The same machine runs the services your business uses every day.
Every fleet is different. We size each machine with you and help you source it from any vendor.
| Role | AI and inference, plus your everyday apps |
|---|---|
| Runs on | A machine you own, or one we help you choose and source |
| Needs | Graphics cards sized for the models you want to run |
| Works with | Gateway, Sentinel, Workshop and May |
| Managed by | Onyx, on the same screen as the rest of your fleet |
| Software | Onyx, set up in this role on your machine |
|---|---|
| Hardware | Yours. We help you choose and source it from any vendor, and you buy direct. |
| Managed service | Optional add-on: we watch and look after the machine for you |
The AI models you choose, plus the services your business runs every day.
Yes. May's model runs on the graphics cards of a machine in the Compute role.
That depends on the models you want to run. We size it with you and help you source it from any vendor.
