ELIXR-B
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,Northwestern Medicine,Apollo Radiology International
- Organisation type
- Industry
- Country
- United States of America, India
- Published
- 7 September 2023
- Authors
- Shawn Xu, Lin Yang, Christopher Kelly, Marcin Sieniek, Timo Kohlberger, Martin Ma, Wei-Hung Weng, Atilla Kiraly, Sahar Kazemzadeh, Zakkai Melamed, Jungyeon Park, Patricia Strachan, Yun Liu, Chuck Lau, Preeti Singh, Christina Chen, Mozziyar Etemadi, Sreenivasa Raju Kalidindi, Yossi Matias, Katherine Chou, Greg S. Corrado, Shravya Shetty, Daniel Tse, Shruthi Prabhakara, Daniel Golden, Rory Pilgrim, …
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision, Medicine
- Task
- Image embedding, Visual question answering, Semantic search, Image classification, Language modeling/generation
- Base model
- PaLM 2,ELIXR-C
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.
- Training data
- tokens
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Unknown
Sources
Where this record came from and when it was last checked.
- Reference
- ELIXR: Towards a general purpose X-ray artificial intelligence system through alignment of large language models and radiology vision encoders
- Last updated
- 28 November 2025
What the numbers mean
What this model is
ELIXR-B was published by Google,Northwestern Medicine,Apollo Radiology International, in the country recorded as United States of America, during September 2023. The publishing organisation is categorised as industry.
It works in the domain of Vision, Medicine, and is recorded as performing the task of image embedding, Visual question answering, Semantic search, Image classification, Language modeling/generation.
Its starting point was an existing base model, PaLM 2,ELIXR-C. That is why it shares the base model's general shape and size.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
Answers
ELIXR-B — common questions
ELIXR-B— when was it released?
It was published in September 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.
ELIXR-B— what is it used for?
It works in the domain of Vision, Medicine, and is recorded as handling the task of image embedding, Visual question answering, Semantic search, Image classification, Language modeling/generation. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.
ELIXR-B— 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.
ELIXR-B— is it open source?
The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
ELIXR-B— how many parameters does it have?
No parameter count has been published for it, which is why no memory or speed figure appears on this page.
ELIXR-B— who created it?
It was published by Google,Northwestern Medicine,Apollo Radiology International, based in United States of America, an organisation categorised as industry.
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.