When running Llama 3.1 on the RTX 4080, GPU utilization averaged around 75% with spikes to 100%, consuming 16GB of host system memory.

factualpending

Speaker

Dave

Evidence Quote

it's averaging around 75% GPU with spikes up to 100

Source

Run Local LLMs on Hardware from $50 to $50,000 - We Test and Compare!Dave's Garage
Created: 8/13/2026, 9:51:22 AM

My Notes

Loading notes...