knowyourai
Is the model on your machine the model it claims to be?
You pulled a 5 GB file from a stranger's repo. The model card says which model it is and that nothing odd happens when you chat with it. knowyourai checks those claims against the bytes, and tells you when something changes after you approved it.
- In the 200 most-downloaded GGUF repos on Hugging Face (October 2026), 61 of the 128 comparable chat templates differ from the declared base model's. A chat template is a program that runs on every prompt.
- Never runs a model. It reads headers and metadata: no torch, no GPU, no dependencies, offline by default, no telemetry.
- Checks a Hub repo before you pull it. A 471 GB repo takes about 9 seconds and downloads nothing.
- A lockfile for models: lock pins what you approved, check fails CI when it moves.
Know the limit
Most template differences are deliberate fixes by the quantizer. A finding means read it, not that the model is malicious, and consistent is never the same as safe.
$ uvx knowyourai scan
STATUS COMPONENT FORMAT SIZE
review hf:someone/Model-GGUF gguf Q4_K 4.4 GB
consistent hf:org/embedding-model safetensors F32 87.3 MB
hf:someone/Model-GGUF
[high] TMPL002 Chat template changes behaviour when a
message contains specific text
evidence: model.gguf#chat_template: branches on 'wire the funds'