models · nvidia

Llama-3.1-Nemotron-Ultra-253B-v1

NVIDIA's 253B ultra model distilled from frontier models. Top open-weight reasoning.

Compare Verify

What this registry has checked

Quarantine. We hold the publisher’s own published hash for these weights and have recorded it against this entry. We have not downloaded and hashed the weights ourselves, so the hash is the publisher’s claim, not our measurement.
Weight file SHA-2566d5c8ac78f27a83a8961236297c7b76cdfc84cfb4326e4ecae0db18b9e48a737
Methodhf-published-sha256
Re-check this yourself → Source → Full record →

What is recorded

Publishernvidia
OriginUnited States
LicenceLlama-3.1
Publisher’s own licence statementother
Parameters253,401,268,224 (253.4B)
Architecturenemotron-nas
Layers162
Hidden size16384
AttentionMHA (128 heads, 128 KV)
Native precisionBF16
Pulls recorded here36,006
Downloads reported upstream1,634

Reported scores

MMLU-Pro82.5
GPQA Diamond72.8
AIME 202563.7
MATH-50095.2
LiveCodeBench64.1
IFBench38.2
Humanity's Last Exam7.4

Reported by a third party and recorded here, not re-run by us. Source: artificialanalysis.ai/api/v2.

Elsewhere in the registry

All models → Browse with filters → What will run on my hardware? →

Registry record as of 2026-09-01. Identity, licence and parameter count are properties of a release and do not move; tier can, and the verify link above re-checks it against the live registry rather than this page.