CELLE-2
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
- Chan Zuckerberg Initiative,University of California San Francisco,University of California (UC) Berkeley
- Organisation type
- Research collective,Academia,Academia
- Country
- United States of America
- Published
- 10 October 2023
- Authors
- Emaad Khwaja, Yun Song, Aaron Agarunov, Bo Huang
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- Protein localization prediction, Text-to-image
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
- 4,327,372 tokens
Image tokens: 17,268 × 256 = 4,420,608 Sequence tokens: 17,268 × 400 = 6,907,200 Total: 4,420,608 + 6,907,200 = 11,327,808 (1.13e7) ['Likely' confidence in dataset size estimation - two estimations slightly differ within same OOM]
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
- Open source
- Hugging Face
- HuangLab
MIT license: https://huggingface.co/HuangLab/CELL-E_2_HPA_Finetuned_480 MIT license: https://github.com/BoHuangLab/CELL-E_2
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Likely
- Citations
- 3
Sources
Where this record came from and when it was last checked.
- Reference
- CELL-E 2: Translating Proteins to Pictures and Back with a Bidirectional Text-to-Image Transformer
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
CELLE-2 was published by Chan Zuckerberg Initiative,University of California San Francisco,University of California (UC) Berkeley, in the country recorded as United States of America, during October 2023. The category the publisher falls under is research collective,Academia,Academia.
It works in the domain of Biology, and is recorded as performing the task of protein localization prediction, Text-to-image.
Published weights mean the model runs on your machine rather than someone else's, which is what makes the hardware question below answerable at all. On Hugging Face it is published under the organisation HuangLab.
How it was trained
It was trained on a corpus of about 4,327,372 tokens of text.
Answers
CELLE-2 — common questions
CELLE-2— what GPU do I need to run it?
We cannot say. It 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.
CELLE-2— is it open source?
Its weights are published, so it 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.
CELLE-2— 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.
CELLE-2— who created it?
It was published by Chan Zuckerberg Initiative,University of California San Francisco,University of California (UC) Berkeley, based in United States of America, an organisation categorised as research collective,Academia,Academia.
CELLE-2— when was it released?
It was published in October 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.
CELLE-2— what is it used for?
It works in the domain of Biology, and is recorded as handling the task of protein localization prediction, Text-to-image. These are the areas it was designed around; they describe intent rather than a hard boundary.
CELLE-2— where can I download it?
Its weights are published on Hugging Face, under the organisation HuangLab. We do not host model files — this site calculates what hardware is needed to run them.
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.