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 I wrote the GB10 off as a sidecar: 6.4 tok/s per stream, bound by memory bandwidth. On 31 October the same model ran on the same machine at 148.5 tok/s — because bandwidth was never the ceiling, the stack underneath was. Measured here: speed across session counts, window counts, refusal rates, the memory arithmetic and joules per token.
YaRN stretching to 524,288 and 1,048,576 context tokens, three KV tiers, 20 cells: 24 of 24 probes found, the timing probe still reports 2,000 tok/s — but a full pass costs 5.8 to 13.7 minutes.
KV cache from fp16 to q4_0, 8,192 to 262,144 tokens, one to eight sessions on two RTX 3090s: the bottleneck is time to first token, the KV tier moves it by 64 seconds — and no tier loses the needle.
05 Contact
Based in Europe. Always happy to chat about homelab stuff, AI, or whatever you're building.