Homelab + AI + Self-hosting
Tinkering with servers, running local AI models, and connecting it all together. I self-host everything I can and document the journey here.
Say hi01 What I do
Mostly servers, AI setups, and whatever rabbit hole I fall into next.
Proxmox clusters, LXC containers, VMs for everything. I like building infrastructure that just runs, even when I forget about it for weeks. Multiple nodes at home and in data centers, all connected through a mesh VPN.
Running LLMs and image generation on my own hardware. No cloud APIs, no per-token billing. Just a GPU doing its thing on a shelf in my room.
Web hosting, email, DNS, git repos, CI runners. If there's a self-hosted alternative, I'm probably running it somewhere.
Pipelines, deployment scripts, and AI agents that do the boring stuff so I don't have to. Still tweaking, always tweaking.
Encrypted tunnels everywhere, key-only SSH, firewall rules, monitoring. Not because I'm paranoid, but because getting hacked would be really annoying.
02 Projects
Side projects, tools I built for myself, and things that started as "this should be quick" and never were.
03 The Stack
A mix of dedicated servers, mini PCs, and a GPU workstation, all stitched together with Tailscale.
Proxmox VE clusters with a bunch of VMs and containers. Dedicated servers in data centers plus a few machines at home. Overkill for one person, but that's kind of the point.
An RTX 3090 running Ollama and ComfyUI, serving local AI to every machine on the network. No cloud, no API keys, no monthly bills.
Tailscale mesh VPN connecting everything. Home, data center, laptop, phone. Every connection encrypted, every device reachable by name.
Dashboards, alerting, automated backups. I get a notification before things break, and snapshots so I can roll back when I inevitably break something myself.
04 Latest
Write-ups about things I've built, broken, and eventually fixed.
On 21 October the model ran on the GB10 at 6.4 tok/s per session, on 31 October at 76.2 tok/s. The difference came from the stack underneath: vLLM instead of llama.cpp, FP4 weights, fp8 KV memory, three seats. Part of that factor is my first llama.cpp configuration, which I never checked. That measurement is still outstanding.
Twelve cells of rope stretching beyond the trained frame: 24 of 24 needles found, at scale 2 and scale 4. But one full pass costs 5.8 minutes at 512k and 13.7 minutes at one million tokens, and the rate falls from 2,053 to 1,210 tokens per second. Both k8v4 double cells at 512k collapsed; I have no explanation for that.
Two nights, 112 measurement cells: 262,144 tokens of context cost 139 to 219 seconds of waiting, 131,072 tokens cost 66 seconds. The KV tier shifts that wait by up to 64 seconds and loses no needle test — q4_0 stays the choice. The machine sweet spot is 131,072 tokens times eight conversations. Every cell ships as JSON and CSV inside the post.
05 Contact
Based in Europe. Always happy to chat about homelab stuff, AI, or whatever you're building.