Trains on your data by default
= no (Favourable)Ollama processes cloud prompts and responses to answer your requests. We do not use them to train models.
service ollama-cloudvendor Ollamacategory Inference hosts & routers
No (Favourable)
Ollama processes cloud prompts and responses to answer your requests. We do not use them to train models.
Prompts and responses are not stored beyond the request.
this content is not stored beyond the time required to fulfill the request.
Against the 21 tools that state a period (grey dots):
Ollama says it requires no-logging and ZDR terms from the NVIDIA Cloud Providers that host its models.
When Ollama partners with providers, we require no logging, no training, and zero data retention policies in place.
Ollama says cloud prompts and responses are never logged, and its model partners must have no-logging and zero-retention policies. The privacy policy lists fraud and abuse prevention using account, device and usage data; its diagnostic metadata excludes prompt content.
Prompt or response data is never logged or trained on.
No region choice.
Ollama hosts models and compute resources primarily in the United States. To serve global demand, we may route to Europe for additional capacity.
No certification statement found.
no official page stated this clearly
Not stated.
no official page stated this clearly
The same tool runs models entirely on your machine; cloud features can be disabled.
We don’t see your prompts or data when you run locally.
Spotted something wrong or out of date? Corrections are welcome; see how to send one. How statuses are assigned.