BF16 MFU gain on H100 (GPT-3 175B) from software and kernel maturation over ~12 months, Jan–Dec 2024, on unchanged silicon
34% → 54%observed
| Value kind | observed — Reported measurements, counts, and specifications keep the precision and scope stated by their source; an exact specification is not treated as a range. |
|---|---|
| Scope | Measured on a 128-H100 cluster, January-December 2024, as BF16 MFU against the H100's dense BF16 peak. The endpoints are rounded MFU percentages, so the ratio of the two (54/34) is approximate. |
| As of | 2024-12 |
| Source | SemiAnalysis, H100 vs GB200 NVL72 Training Benchmarks, 2025-08-20 · Section 'GPT-3 175B Token/s/GPU, Training Performance and Power. Cost Improvements from January 2024 to December 2024': 'a considerable improvement from 34% MFU to 54% MFU over the course of 12 months' |
| Review | checking…review by 2027-10-19 · standard cadence |
| Recorded changes | last 2026-10-16 · 2 revisions tracked |
| Claim id | bf16-mfu-gain-on-h100-gpt-3-175b-from-software |
Where the guide uses it
← Full numbers register — every date-stamped figure in the guide, with revision history.