Search & explore

• Level L05
• T11
• 21 min read

Run a self-hosted AI server that many people rely on, month after month: watch five signals, measure how many people it serves at once, set a limit below the breaking point, compare its cost per 1,000 answers with an API, and hand it to a second operator with records an auditor can check.

Matching textT11-L05 · Run your own AI · Level 5 Operator · 22-minute read, plus 3 hours of doing Keep a Shared Model Server Fast, Affordable and Running Monday, 09:10 In a lab it's six

• Level L04
• T11
• 23 min read

Move a self-hosted assistant from one computer to a server the whole team can reach: one HTTPS address, a firewall that lets nothing else in, the model port closed, named accounts, backups you have restored, and an update you can undo. IT and the data protection officer sign off before the first colleague logs in.

Matching textT11-L04 · Run your own AI · Level 4 Integrator · 22-minute read, plus 3 hours of doing Put Your Team's Assistant on a Server Colleagues Can Reach The assistant everyone has to walk

• Level L03
• T11
• 24 min read

Run local AI apps with Heidelberg AI Desk so colleagues can depend on the result: install Desk and let it set up Podman, read what an app needs before it changes anything, find where its data lives, back it up, restore it on a second computer, update it safely, and know when a laptop is no longer enough.

Matching textT11-L03 · Run your own AI · Level 3 Builder · 21-minute read, plus 90 minutes of doing Local AI Apps Your Colleagues Can Rely On When your laptop becomes the group's printer In

• youtube
• 10 min video

Install LM Studio, download a fitting model and start local chat on Windows. Windows-specific; not proof of offline operation or current sizing.

Matching textT11-L01: Follow the Windows installation, model download and first graphical chat. Stop before the later developer/server and remote-link tour. The recording does not verify today's model sizing…

• youtube

Connect an Open WebUI client to an LM Studio model server. 2024 Fedora/Python setup, not AI Desk/Podman; current auth and network defaults differ.

Matching textT11-L02: Watch 2:00 for the model server and 5:24 for connecting Open WebUI to its API. This 2024 Fedora/Python installation differs from Heidelberg AI Desk and Podman. Skip the later LAN/mobile-access…

• youtube

Back up and restore named container volumes across hosts. Docker commands differ from Podman; doesn't prove application-consistent database backups.

Matching textT11-L03: Watch from 3:52 for named-volume access and backup, restore and migration. This 2021 Docker example teaches the storage operation, not Podman commands or Heidelberg AI Desk. Follow the…

One-page diagram to use with T11-L05, "Keep a Shared Model Server Fast, Affordable and Running".

One-page diagram to use with T11-L02, "A Local Model Your Tools Can Call".

One-page diagram to use with T11-L02, "A Local Model Your Tools Can Call".