Local AI, from people who run it

Run AI on your own hardware.

Probing your GPU

Test it out in the Studio

Your GPU is read by your browser and never sent to us. Speeds are estimates unless marked measured. Measured something on your own rig? Send it to us.

Go deeper

Everything else, one click away

01StudioMake images and chat on your own GPU. Install it; it works offline.02LearnGuides to VRAM, models, used GPUs and Ollama, from people who run it.03Every GPUWhat any card or Mac can run, with speeds and the command to start.04BuildsSet a budget, get a parts list with used prices.05PodcastAll things AI, run it local. New episodes and lab notes by email.06PostsMeasured runs, fixes and builds, from our rack and from you. Send yours in.07PeopleThe engineers behind the rack.