AI RESEARCH
RooflineBench: A Benchmarking Framework for On-Device LLMs via Roofline Analysis
arXiv CS.AI
•
ArXi:2602.11506v3 Announce Type: replace-cross The transition toward localized intelligence through Small Language Models (SLMs) has intensified the need for rigorous performance characterization on resource-constrained edge hardware. However, objectively measuring the theoretical performance ceilings of diverse architectures across heterogeneous platforms remains a formidable challenge. In this work, we propose a systematic framework based on the Roofline model that unifies architectural primitives and hardware constraints through the lens of operational intensity (OI