01
Local LLM Benchmark Lab
A personal Windows PowerShell benchmark for llama.cpp. It records repeatable test settings, raw output, prompt and generation throughput, and structured CSV results as I extend hardware monitoring.
Read the benchmarkProjects
Experiments with evidence.
These projects are part build log, part learning system: practical work with enough measurement and documentation to make the results useful again.
02
Home Server Architecture
A design exploration, not a completed build: a power-conscious home server with redundant storage, virtual machines, secure remote access, and room for a future GPU.