VBVlad Butacuinomniforge.online·May 4 · 9 min readGreen AI at the Edge: When Local LLMs Save Electricity and WaterAI sustainability keeps getting framed around the wrong question: does a local LLM use less electricity and water than ChatGPT or Claude? The sharper question is: how many frontier-model calls are we 00
VBVlad Butacuinomniforge.online·Apr 15 · 5 min readOmniForge Desktop: Local-First Document Intelligence for macOSIf you've ever needed to ask a question across a dozen PDFs and a week of meeting recordings, you know the drill. Open four apps. Search each one separately. Copy-paste between tabs. Reconstruct conte00
VBVlad Butacuinomniforge.online·Apr 15 · 8 min readYour Local LLM Is Slow Because of Five Config FlagsYour model fits in memory. You load it up, send a prompt, and watch it choke halfway through a conversation. Or it runs, but at 3 tokens per second on hardware that should do better. You picked the ri00
VBVlad Butacuinomniforge.online·Apr 7 · 5 min readWe Automated the Parts of Development Nobody Wants to DoIf you've worked on a team with more than a couple of developers, you know the drill. Someone opens a merge request. It sits there. Eventually someone reviews it, but by then the author has moved on t00
