MultiverSeg

Open weights Massachusetts Institute of Technology (MIT),Databricks August 2025

No estimate

No hardware requirements for this model

This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.

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
Massachusetts Institute of Technology (MIT),Databricks
Organisation type
Academia,Industry
Country
United States of America
Published
31 August 2025
Authors
Hallee E. Wong, Jose Javier Gonzalez Ortiz, John Guttag, Adrian V. Dalca

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Vision, Biology, Medicine
Task
Image segmentation

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

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
Open — downloadable
Model access
Open weights (unrestricted)
Training code
Unreleased

Apache 2.0 https://github.com/halleewong/MultiverSeg

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
MultiverSeg: Scalable Interactive Segmentation of Biomedical Imaging Datasets with In-Context Guidance
Last updated
28 November 2025

What the numbers mean

Background

MultiverSeg was published by Massachusetts Institute of Technology (MIT),Databricks, in United States of America, in August 2025. The organisation is categorised as academia,Industry.

It works in Vision, Biology, Medicine, and is recorded as doing image segmentation.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.

Answers

MultiverSeg — common questions

01

Is MultiverSeg open source?

Its weights are published, so MultiverSeg can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.

02

How many parameters does MultiverSeg have?

No parameter count has been published for MultiverSeg, which is why no memory or speed figure appears on this page.

03

Who created MultiverSeg?

MultiverSeg was published by Massachusetts Institute of Technology (MIT),Databricks, based in United States of America, categorised as academia,Industry.

04

When was MultiverSeg released?

MultiverSeg was published in August 2025.

05

What is MultiverSeg used for?

MultiverSeg works in Vision, Biology, Medicine, and is recorded as handling image segmentation. 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.

06

Where can I download MultiverSeg?

The weights for MultiverSeg are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

07

What GPU do I need to run MultiverSeg?

We cannot say. MultiverSeg has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.

Source

Original publication

Record last updated 28 November 2025

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.