GreyBrain · The model formulary

You would read the insert
before you prescribe.

Every one of these models comes with a note from the people who built it — who they are, what it learnt from, whether you may use it and where it stops. We read that note and set it out plainly. Nothing is invented, and a field marked not stated means the makers did not say, which is itself worth knowing before you rely on it.

google

medgemma-4b-it

Google's medical model. It takes an image and a history together, so it is the one people point to when they claim AI can read a scan. Worth knowing what Google itself claims, and what it does not.

image-text-to-text · 4,49,805 downloads

m42-health

Llama3-Med42-8B

Built by a hospital group, tuned on medical material, and open enough that you can look at what went into it instead of taking the claim on trust.

text-generation · 2,085 downloads

lingshu-medical-mllm

Lingshu-7B

Answers questions about a medical image rather than only about text. The kind of model behind an imaging demo at a conference stall.

image-text-to-text · 9,246 downloads

aaditya

Llama3-OpenBioLLM-8B

Openly published, widely quoted in AI-in-medicine talks, and often shown with a benchmark score. Useful for seeing what such a score actually rests on.

text-generation · 2,175 downloads

FreedomIntelligence

HuatuoGPT-o1-8B

Trained to show its reasoning on a medical question, not just hand you an answer. Closer to how you would expect a registrar to present.

text-generation · 608 downloads

epfl-llm

meditron-7b

Built by a university and unusually clear about exactly which medical texts it was trained on — which is what lets you judge where it will be weak.

text-generation · 718 downloads

microsoft

BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext

Trained only on PubMed. It does not chat; it sits underneath the search and screening tools you already use for a literature review.

fill-mask · 19,24,950 downloads

openaiThis week

whisper-large-v3

Speech to text. Most doctors meet this one without knowing it, inside a dictation or transcription app. Worth knowing where your voice note goes.

automatic-speech-recognition · 34,89,398 downloads

Live from Hugging Face · not reviewed by us

The field, this week.

Everything above this line was read and written up by a person. Everything below is a live query, shown so you can see what is actually happening rather than take our word for it. Treat it as a reading list, not a formulary — and nothing here has been checked for clinical use by anyone.

Released this month

Published in the last sixty days and already being downloaded. A model can be days old and have thousands of users.

What everyone is using

The most-downloaded models on Hugging Face right now, across every field. Mostly not medical, and not filtered for clinical use.

Built for medicine

Models whose makers describe them as medical or clinical, with the format re-uploads and mirrors removed.

Facts are read from each model’s published card on Hugging Face. Listing a model here is not an endorsement, a safety assessment, or a recommendation to use it in patient care.

Start free — Day 0 Choosing the right model is module F4 of the starter

← Back to today’s practice

You would read the insertbefore you prescribe.