Med-PaLM 2
No estimate
No hardware requirements for this model
The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- Google Research,DeepMind
- Organisation type
- Industry,Industry
- Country
- United States of America, United Kingdom of Great Britain and Northern Ireland
- Published
- 16 May 2023
- Authors
- Karan Singhal, Tao Tu, Juraj Gottweis, Rory Sayres, Ellery Wulczyn, Le Hou, Kevin Clark, Stephen Pfohl, Heather Cole-Lewis, Darlene Neal, Mike Schaekermann, Amy Wang, Mohamed Amin, Sami Lachgar, Philip Mansfield, Sushant Prakash, Bradley Green, Ewa Dominowska, Blaise Aguera y Arcas, Nenad Tomasev, Yun Liu, Renee Wong, Christopher Semturs, S. Sara Mahdavi, Joelle Barral, Dale Webster, Greg S. Corra…
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Medicine, Language
- Task
- Question answering
- Base model
- PaLM 2
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Parameters
- 340B
- Training data
- 16,020,450 tokens
from PaLM 2
Dataset Count Mixture ratio MedQA 10,178 37.5% MedMCQA 182,822 37.5% LiveQA 10 3.9% MedicationQA 9 3.5% HealthSearchQA 45 17.6% MedMCQA (https://proceedings.mlr.press/v174/pal22a/pal22a.pdf, Table 2) has on average 12.77+ 2.69+67.52 = 82.98 tokens per datapoint
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Closed — provider access only
- Model access
- Unreleased
- Training code
- Unreleased
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Why it is tracked
- SOTA improvement
- Record confidence
- Likely
https://paperswithcode.com/sota/question-answering-on-medqa-usmle "Med-PaLM 2 scored up to 86.5% on the MedQA dataset, improving upon Med-PaLM by over 19% and setting a new state-of-the-art. We also observed performance approaching or exceeding state-of-the-art across MedMCQA, PubMedQA, and MMLU clinical topics datasets."
Sources
Where this record came from and when it was last checked.
- Reference
- Towards Expert-Level Medical Question Answering with Large Language Models
- Last updated
- 28 November 2025
What the numbers mean
About this model
Med-PaLM 2 was published by Google Research,DeepMind, in the country recorded as United States of America, during May 2023. The category the publisher falls under is industry,Industry.
It works in the domain of Medicine, Language, and is recorded as performing the task of question answering.
Rather than being trained from scratch, it is derived from PaLM 2. That is the usual way a specialised model is produced.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
How it was trained
It was trained on a corpus of about 16,020,450 tokens of text.
Its inclusion criterion: sOTA improvement.
Answers
Med-PaLM 2 — common questions
Med-PaLM 2— who created it?
It was published by Google Research,DeepMind, based in United States of America, an organisation categorised as industry,Industry.
Med-PaLM 2— when was it released?
It was published in May 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
Med-PaLM 2— what is it used for?
It works in the domain of Medicine, Language, and is recorded as handling the task of question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.
Med-PaLM 2— what GPU do I need to run it?
None. This is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.
Med-PaLM 2— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
Med-PaLM 2— how many parameters does it have?
It has a parameter count of 340B. from PaLM 2. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.