Larvitz Blog
Mastodon

Welcome to Larvitz Blog! I’m Christian, a Senior Consultant by day and FreeBSD enthusiast by night, with over 20 years in enterprise IT. Here I write about FreeBSD jails, PF firewalling, self-hosting, Linux system administration, and anything that’s cleanly engineered. Most articles are hands-on guides born from running my own infrastructure, from dual-stack networking and Ansible automation to hosting a Mastodon instance on FreeBSD.

Have a question or want to discuss something? Find me on the Fediverse at @Larvitz@burningboard.net. I’m always happy to chat!

#ai Articles

Claude Code on a FreeBSD Desktop: Plasma, xrdp, the Linuxulator and One Very Confusing PATH

A FreeBSD 15.1 Plasma desktop in a Proxmox VM, reachable over xrdp, running Claude Code as a Linux binary through the Linuxulator. Along the way: an Xorg that found no screens, a KRDP package that does not exist, a VirtIO-GPU that gives you a framebuffer but no acceleration, and a “version regression” that turned out to be two Claude installations fighting over my PATH. Then I let the agent firewall the machine it was running on, and it did that more carefully than I usually do. It also got one thing wrong, and of course it was the thing about root.
  • Sat 03 October 2026
  • Linux

Self-Hosted AI: Qwen 3.8 on a Rented Blackwell at 150 Tokens per Second

An open-weight Qwen 3.8 27B model, an RTX PRO 6000 Blackwell rented by the hour, and one shell command to start it. For most of my everyday coding it is good enough, it answers at roughly 150 tokens per second, and my prompts stay on infrastructure I chose. Some honest caveats about what “self-hosted” means on someone else’s GPU are included, along with the workflow that has worked best for me: a frontier model for architecture, and a fast open-weight model for the token-heavy implementation loop.
  • Wed 03 June 2026
  • Meta

The AI Stack I Actually Run in 2026: A Laptop iGPU and Four Rented Frontiers

The most interesting thing about AI in 2026 is not which frontier model wins this month’s benchmark. It is that the frontier became a commodity you rent through near-interchangeable clients, while the part with actual craft in it moved onto the integrated Radeon 780M in my laptop. Here is the tiered stack I actually run, with the local layer in detail because that is the unusual part, and the cloud layer kept brief because the pricing is on the vendors’ own pages and will be wrong by autumn.