AI assistants
LM Studio privacy rating
Desktop app for finding, downloading and running large language models locally, with a chat interface and a local API server.
Summary
LM Studio scores 72 out of 100 (grade C) on the AI assistants criteria. It meets 6 of 8 criteria: no trackers or telemetry, no ads or data sales, no training on your data, runs locally, limited chat retention and no account needed. It does not meet open source and independent audit.
Score 72 out of 100. How scoring works
Criteria
-
No
Open source Weight 3 of 3
Is all the source code needed to run the product public?
Closed source. The lms command-line tool and SDKs are open source, but the app is not.
-
Yes
No trackers or telemetry Weight 3 of 3
Are the website and apps free of third-party trackers, with any analytics anonymous and any telemetry off by default?
No third-party trackers, and the app contacts LM Studio only for updates and model downloads. The website's Plausible analytics are cookieless and aggregate-only.
-
Yes
No ads or data sales Weight 2 of 3
Is the product funded without advertising, ad targeting or selling user data?
Free to use, funded by paid enterprise plans, with no ads.
-
No
Independent audit Weight 2 of 3
Has an independent security or privacy audit been published within the last three years?
No independent audit is published.
-
Yes
No training on your data Weight 3 of 3
Are prompts, chats and files kept out of model training by default?
Prompts and responses stay on the device and are not retained by LM Studio.
-
Yes
Runs locally Weight 2 of 3
Can the assistant run on your own device or server, so prompts never leave it?
Models run entirely on the user's own computer and can work offline.
-
Yes
Limited chat retention Weight 2 of 3
Are chats deleted by default or on request, with no long-term server copy?
Chats are stored only on the device.
-
Yes
No account needed Weight 1 of 3
Can it be used without an account or personal details?
No account is needed.