ai model report

Is nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 safe to load?

LOW risk. 5 of 321 tracked dependencies carry advisories. Driven by No version-matched advisories and no malicious packages..

View on HuggingFace

// posture

fig. 01 — posture on eight axes, 100 is clean. Weakest: code execution at 25.

// the finding

0.0xyz score out of 10LOW

MEDIUMconfig.json declares `auto_map` — from_pretrained(trust_remote_code=True) executes Python shipped in this repo.

2 more findings on this model.

Author: nvidia
Task: text-generation
Loader: transformers
License: other
Downloads: 475,437
Remote code: ships Python that runs on load (trust_remote_code)

// dependencies

13 direct, 9 with findings, 312 reachable

Package	Evidence	Advisories	Worst
vllm	direct, runtime	72	none pinned
transformers	direct, runtime	23	none pinned
torch	direct, install	13	hidden
numpy	direct, install	8	hidden
mamba-ssm	direct, install	1	hidden
causal-conv1d	direct, install	0	hidden
huggingface-hub	direct, install	0	hidden
safetensors	direct, install	0	hidden

Create a free accountto see all 321 dependencies, which versions are pinned, and what to change.

// what changed

MEDIUMvector new2026-09-09
MEDIUMrisk level raised (unknown to low)2026-09-09

Risk computed 2026-09-22 at 18:59 UTC. Dependencies come from the model's requirements, its declared loader and the code it ships; advisories from NVD, GHSA and OSV.