Blog

Longer arguments about why any of this is worth doing on your own hardware. Written by the people who keep the fleet running, and opinionated where we have a view.

Private AI

What leaves the building when a team uses someone else's model, and what does not have to.

Agents and automation

The work that pays for the machine is usually unattended, not chat.

Want the hands-on version?

The docs cover the commands: SSH keys, vLLM flags, model sizing and benchmarks we ran ourselves.

Read the docs Deploy a Spark