Upload .gguf, .onnx, or .safetensors. Validate artifact integrity, unsafe patterns, and applicable runtime advisories. Get HTML/JSON reports and integrate via API.
General awareness feed from NVD — not matched against any specific model you scan. Per-scan CVE findings (when applicable) appear inside that scan's own report.
A scan isn't just "read the header" — every artifact is assessed across four areas, with format-specific checks where applicable. Full detail in How it works.
A scan assesses an artifact's integrity, structure, provenance signals, and deployment risks — but it can't tell you whether someone quietly edited a model's weights after the fact — a targeted fact-edit (ROME/MEMIT-style), a suppressed behavior, a fine-tune that went further than intended. Two files with different numeric content can produce identical structural scan reports — same hashes aside, everything else matches. Compare inspects tensor content directly, one tensor at a time, to answer the question a hash can't.
Two checkpoints of a 124M GPT-2 model, same architecture, run through Compare:
The edit is localized to a single feed-forward projection in the first transformer block — every other tensor (147 of 148, same names, shapes and byte content) is identical. That's a fingerprint a file hash alone would completely miss. (Compare diffs tensor content, not GGUF metadata like tokenizer config — see How it works.)
LLMScan also classifies the observed change pattern, localizes affected model regions, and summarizes whether changes are metadata-only, localized, broadly distributed, or structural. For numeric tensors it reports relative L2, RMS, changed-element density, percentiles, cosine similarity, and difference distribution.
Free with an account — 10 comparisons/month on the Free plan.
Get an API key from your dashboard to scan files programmatically.
curl -X POST https://llmscan.online/api/scan -H "Authorization: Bearer <api_key>" -F "file=@/path/to/model.gguf"
Sign up on the Free plan, then contact us for Pro access.