ai model report

Is autotrust/Qwen3.8-Flash-Next-E384-FP4-V2 safe to load?

CyberXYZ rates autotrust/Qwen3.8-Flash-Next-E384-FP4-V2 LOW. No version-matched advisories and no malicious packages. It depends on 225 tracked packages, and 4 carry advisories. It does not require trust_remote_code. A mixed serialization signal is recorded for it; the model_load_safety tool gives the per-file verdict.

View on HuggingFace

// posture
advisories 100provenance 45resolution 100xyz safety 100load safety 60supply chain 100scanner trust 100code execution 70
fig. 01 — posture on eight axes, 100 is clean. Weakest: provenance at 45.
// the finding
not scoredno advisory applies to a version this model pinsLOW

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

3 more findings on this model.

Author
autotrust
Task
image-text-to-text
Loader
vllm
License
other
Downloads
42,718
Remote code
not required
// dependencies

13 direct, 10 with findings, 218 reachable

PackageEvidenceAdvisoriesWorst
vllmdirect, runtime112none pinned
transformersdirect, authored24none pinned
Create a free accountto see all 225 dependencies, which versions are pinned, and what to change.
// questions
Is autotrust/Qwen3.8-Flash-Next-E384-FP4-V2 safe to load?

CyberXYZ does not call a model safe in absolute terms. It rates autotrust/Qwen3.8-Flash-Next-E384-FP4-V2 LOW. No version-matched advisories and no malicious packages. That covers its dependencies and how it loads, not every file it ships, so treat any check that did not run as unverified and check the exact files before you load them.

What does autotrust/Qwen3.8-Flash-Next-E384-FP4-V2 depend on?

CyberXYZ tracks 225 dependencies for autotrust/Qwen3.8-Flash-Next-E384-FP4-V2, 13 of them direct. 4 carry advisories. They include vllm and transformers. A free account lists all of them.

Does autotrust/Qwen3.8-Flash-Next-E384-FP4-V2 run code when it loads?

HuggingFace does not mark autotrust/Qwen3.8-Flash-Next-E384-FP4-V2 as requiring trust_remote_code. That says nothing about the format of its weight files, which model_load_safety checks per file.

How do I check autotrust/Qwen3.8-Flash-Next-E384-FP4-V2 before loading it?

Run the xyz MCP tool model_load_safety on autotrust/Qwen3.8-Flash-Next-E384-FP4-V2 to get a verdict on its weight files before you load them, or search it in CyberXYZ Check at https://cyberxyz.io/check?q=autotrust%2FQwen3.8-Flash-Next-E384-FP4-V2.


Risk computed 2026-11-14 at 13:43 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.