Papers › MedMobile: A mobile-sized language model with expert-level clinical capabilities

MedMobile: A mobile-sized language model with expert-level clinical capabilities

11 Oct 2024arXiv:2410.09019archive 2025-07-28

Krithik Vishwanath, Jaden Stryker, Anton Alaykin, Daniel Alexander Alber, Eric Karl Oermann

Language models (LMs) have demonstrated expert-level reasoning and recall abilities in medicine. However, computational costs and privacy concerns are mounting barriers to wide-scale implementation. We introduce a parsimonious adaptation of phi-3-mini, MedMobile, a 3.8 billion parameter LM capable of running on a mobile device, for medical applications. We demonstrate that MedMobile scores 75.7% on the MedQA (USMLE), surpassing the passing mark for physicians (~60%), and approaching the scores of models 100 times its size. We subsequently perform a careful set of ablations, and demonstrate that chain of thought, ensembling, and fine-tuning lead to the greatest performance gains, while unexpectedly retrieval augmented generation fails to demonstrate significant improvements

PaperPDFCode

Code

nyuolab/MedMobile officialmentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language ModelingLanguage ModellingQuestion AnsweringRetrievalRetrieval-augmented Generation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering MedMCQA Dev MedMobile (3.8B) Accuarcy 63.2 #1 of 1 Archive leaderboard report
Question Answering MedQA MedMobile (3.8B) Accuracy 75.7 #6 of 27 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

SET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections