longest documented NVFP4 pre-training run — Nemotron 3 Super, a 120B-total / ~12B-active hybrid Mamba-Transformer MoE, 25T total seen tokens
25T tokensobserved
| 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. |
|---|---|
| Caveat | Nemotron 3 Super: 120B total / ~12B active hybrid Mamba-Transformer MoE, 25T total seen tokens pre-trained in NVFP4. Nemotron 3 Ultra (June 2026, 550B total / 55B active) is the larger model but saw fewer tokens: 20T text tokens in NVFP4. |
| As of | 2026-10 |
| Source | NVIDIA, Introducing Nemotron 3 Super (2026-03-11) · Introducing Nemotron 3 Super: 25T total seen tokens pretrained in NVFP4 |
| Review | checking…review by 2026-11-23 · standard cadence |
| Recorded changes | last 2026-10-15 · 3 revisions tracked |
| Claim id | longest-documented-4-bit-pre-training-run-12b |
Where the guide uses it
← Full numbers register — every date-stamped figure in the guide, with revision history.