I'm running a 284-billion-parameter model locally, and it competes with cloud AI

XDA developers | July 18, 2026, 1 p.m. | Original
DeepSeek V4 Flash can be run locally thanks to some wizardry, and it works really well.
AMD's 128GB AI mini PC runs models your RTX 5090 can't, but for everything else a used graphics card still wins Your first home lab shouldn't be a NAS — here's why a used business PC does it better