Skip to content
← Models
Open weightsTU Munich/10 trustMetrics-checked

MedAlpaca

Open-source collection of medical conversational AI models and training data.

Visit official page →

About

MedAlpaca was released in April 2023 by researchers at the Technical University of Munich and partners as an open-source collection of medical conversational AI models plus training data. Built on a dataset of over 160,000 entries crafted for medical fine-tuning, it adapts LLaMA-family base models for medical question answering and dialogue, with reproducible training and inference code on GitHub.\n\nThe code repository is GPL-3.0; the model weights inherit the underlying LLaMA base license terms, so commercial users should verify licensing. It remains a widely referenced early open medical model and dataset release.

Specs

Context window

Pricing

Free quota

API access

Weights

Open weights

Released

April 14, 2023

Benchmarks

Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.

Use cases

medical-dialogueclinical-qamedical-fine-tuning-data

Trust score — 7/10

/10 trustMetrics-checked

Scored 7/10 (metrics tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 108; Trending score 68/100 from researcher assessment.

Sources