(#pdp7oxq) There are other tasks LLM(s) are far better suited for, which are also its downsides, and gawd so expensive and unrealistic to run yourself π€¦ββοΈ Do you know what one of these NVIDIA H100βs cost? π² Thatβs right! π€£ > $50k USD π± And many of the models out there require 8 of these suckers π€£ Each one consumes around ~400W of power each (not including the machine that houses them!)
#r5ihb6q