Blog

Notes and write-ups on things I've built.

• September 7, 2026

  Distributed LLM Inference Over Consumer Hardware: A GPU-Pooling Experiment

  Pooling VRAM across two consumer PCs over a gigabit switch with llama.cpp's RPC backend — testing whether it's actually faster, or just makes bigger models possible at all.

• August 2, 2026

  I Just Wanted a NAS: How a Weekend Storage Project Turned Into a Whole Homelab

  A simple photo-backup project turned into Proxmox, GPU passthrough, DNS, ad-blocking, game servers, and more

• May 15, 2026

  Hello!

  Why I made this blog and what you can get out of it