models · nvidia

Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4

Catalogued from local.ai local-inference benchmark index 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	18,328,194,880 (18.3B)
Native precision	U8
Downloads reported upstream	1,405,475

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	298 tok/s	88.3 GB	ordinary
NVIDIA GeForce RTX 5090 32GB	NVFP4	283 tok/s	27.5 GB	ordinary
NVIDIA RTX 6000 Ada 48GB	NVFP4	209 tok/s	42.7 GB	ordinary
NVIDIA DGX Spark 128GB	NVFP4	55.5 tok/s	108.3 GB	ordinary

Measured by local.ai, not by us: 4 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.