ai model report

Is ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit safe to load?

CLEAN risk. 3 of 4 tracked dependencies carry advisories. Driven by No version-matched advisories and no malicious packages..

View on HuggingFace

// posture
advisories 100provenance 75resolution 100xyz safety 100load safety 100supply chain 100scanner trust 100code execution 100
fig. 01 — posture on eight axes, 100 is clean. Weakest: provenance at 75.
// the finding
0.0xyz score out of 10CLEAN

INFOconfig.json was authored against transformers 5.8.1, which has known advisories. Consumers normally install a current version — this only bites if you pin for reproducibility.

1 more finding on this model.

Author
ornith-ai
Task
text-generation
Loader
mlx
Downloads
183,520
Remote code
not required
// dependencies

3 direct, 3 with findings, 1 reachable

PackageEvidenceAdvisoriesWorst
numpydirect, inferred8none pinned
mlxdirect, runtime2none pinned
Create a free accountto see all 4 dependencies, which versions are pinned, and what to change.

Risk computed 2026-09-22 at 18:51 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 ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit safe to load? AI model security report | CyberXYZ