models · nvidia

NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4

Catalogued from llm-stats Open LLM Leaderboard at Quarantine — unverified, pending attestation.

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.

Method	hf-published-sha256

Re-check this yourself → Source → Full record →

What is recorded

Publisher	nvidia
Origin	United States
Licence	unknown
Publisher’s own licence statement	other
Parameters	67,228,556,288 (67.2B)
Architecture	nemotron_h
Layers	88
Hidden size	4096
Attention	GQA (32 heads, 2 KV)
Native precision	U8
Pulls recorded here	6
Downloads reported upstream	2,790,020

Measured on real hardware

None of these runs are ours. Each figure is the reporter’s, linked to their own evidence, under their own trust label. The number shown is single-stream decode — one user, concurrency 1 — because aggregate throughput across many users is a different quantity and reads as far faster than anyone will see.

Measured by local.ai

Hardware	Build measured	Decode @ 8K	Memory @ 8K	Decode mode
NVIDIA RTX PRO 6000 Blackwell 96GB	NVFP4	97.0 tok/s	95.3 GB	ordinary
NVIDIA DGX Spark 128GB	NVFP4	15.6 tok/s	97.4 GB	ordinary

Measured by local.ai, not by us: 2 runs. Each names its engine pinned by image digest and the exact serve command, in the full record.

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.