Hacker News new | past | comments | ask | show | jobs | submit
jackb4040 | on: AirLLM 70B inference with single 4GB GPU
Ahaha thank you, I naively assumed the unlabeled graph in the readme was tps, not spt!
throwawayffffas | parent
Running 292 tps on K3 would make your gpu a money printer.
loading story #49157624