ai model report

Is nvidia/Qwen3.8-27B-NVFP4 safe to load?

LOW risk. 1 of 49 tracked dependencies carry advisories. Driven by No version-matched advisories and no malicious packages..

View on HuggingFace

// posture
advisories 100provenance 70resolution 100xyz safety 100load safety 100supply chain 100scanner trust 100code execution 100
fig. 01 — posture on eight axes, 100 is clean. Weakest: provenance at 70.
// the finding
0.0xyz score out of 10LOW

LOWThe repo's commit SHA changed since we first saw it — weights were replaced.

1 more finding on this model.

Author
nvidia
Task
text-generation
Loader
Model Optimizer
License
apache-2.0
Downloads
83,430
Remote code
not required
// dependencies

3 direct, 1 with findings, 46 reachable

PackageEvidenceAdvisoriesWorst
torchdirect, inferred13none pinned
nvidia-modeloptdirect, runtime0none pinned
Create a free accountto see all 49 dependencies, which versions are pinned, and what to change.

Risk computed 2026-09-22 at 18:52 UTC. Dependencies come from the model's requirements, its declared loader and the code it ships; advisories from NVD, GHSA and OSV.

Model risk is computed from the model's declared and observed Python dependencies and the code it ships. If a finding is wrong, tell us.
Is nvidia/Qwen3.8-27B-NVFP4 safe to load? AI model security report | CyberXYZ