Measuring the Inference Energy Efficiency of Open-Weight LLMs across Benchmarks, Reasoning Modes, and Hardware
arXiv:2610.14389v1 Announce Type: new Abstract: Benchmark scores tell us what an LLM can do, but not how much energy is required to deliver that capability. We directly measure this trade-off for 86 open-weight model checkpoints, evaluated...
Read more: https://arxiv.org/abs/2610.14389
Scan with your phone
Scan with your phone