The Definitive Guide toAI Data Centers
Ask the GuideAboutAccount
GuideGlossaryFLOPS

FLOPS · Floating-Point Operations Per Second

The standard measure of compute throughput; AI clusters are rated in petaFLOPS and exaFLOPS.

Also written as: FLOP · FLOP/s · FLOPs

Current numbers

37–66%MI300X realized inference performance vs H100/H200 despite ~1.3x paper FLOPS — the ROCm goodput gapas of 2025 · register ↗
37–66%MI300X realized inference throughput vs H100/H200 (2025), despite ~1.3x paper FLOPS — the historical realized-MFU gapas of 2025 · register ↗
~30–50%typical model-FLOPS-utilization (MFU) for large LLM training; best-in-class >50% on Hopperas of 2025 · register ↗

← All terms