# Local & private models: where it stands

Open-weight models you can download and run on your own hardware, so patient data never leaves the building. They trail the hosted models in raw ability, but published clinical studies testing them on real tasks, such as flagging urgent patient messages, are starting to appear. Running locally removes one privacy risk, not your other duties.

Notes, newest first (2):

- 2026-11-20 [Study compares cloud and in-house open-weight models for flagging urgent portal messages](https://mddev.health201.com/entry/npj-cloud-vs-local-llm-portal-message-triage-2026/): A Mass General Brigham team led by Valdery Moura Junior and Lidia Moura published a study in npj Digital Medicine comparing six language models for flagging urgent patient-portal messages,…
- 2026-10-21 [DuckDB 2.0 finishes its server mode and adds an Agent Mode for AI coding agents](https://mddev.health201.com/entry/duckdb-2-0-agent-mode-client-server-2026/): DuckDB, a free open-source database that runs inside a single program or on a laptop and is often used to analyze spreadsheets and data exports, released version 2.0.0 ('Cinnamon Teal') on…

From MD-dev, https://mddev.health201.com/stack/local/
