ViT-G/14 (LiT)
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
- Organisation type
- Industry
- Country
- United States of America
- Published
- 15 November 2021
- Authors
- Xiaohua Zhai, Xiao Wang, Basil Mustafa, Andreas Steiner, Daniel Keysers, Alexander Kolesnikov, Lucas Beyer
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Image classification
- Base model
- ViT-G/14
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
- 3B
- Training data
- 1,040,000,000,000 tokens
- Epochs
- 4.5
Table 7
Largest dataset is "4 billion image and alt-text pairs". This is rounded down slightly; the other datasets are much smaller.
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Training hardware
- Google TPU v3
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
- Open source
Apache 2.0 license https://colab.research.google.com/github/google-research/big_vision/blob/main/big_vision/configs/proj/image_text/lit.ipynb https://github.com/google-research/big_vision
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
- Confident
- Citations
- 723
"For example, it achieves 82.5% accuracy on the challenging ObjectNet test set [1], outperforming the previous state-of-the-art method [46] by 10.2%."
Sources
Where this record came from and when it was last checked.
- Reference
- Zero-Shot Transfer with Locked-image Text Tuning
- Last updated
- 25 May 2026
What the numbers mean
Background
ViT-G/14 (LiT) was published by Google Research, in the country recorded as United States of America, during November 2021. The publishing organisation is categorised as industry.
It works in the domain of Vision, and is recorded as performing the task of image classification.
Its starting point was an existing base model, ViT-G/14. 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.
What went into building it
It was trained on a corpus of about 1,040,000,000,000 tokens of text.
The reason it appears in this catalogue at all: sOTA improvement.
Answers
ViT-G/14 (LiT) — common questions
ViT-G/14 (LiT)— what is it used for?
It works in the domain of Vision, and is recorded as handling the task of image classification. These are the areas it was designed around; they describe intent rather than a hard boundary.
ViT-G/14 (LiT)— 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.
ViT-G/14 (LiT)— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
ViT-G/14 (LiT)— how many parameters does it have?
It has a parameter count of 3B. Table 7. 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.
ViT-G/14 (LiT)— who created it?
It was published by Google Research, based in United States of America, an organisation categorised as industry.
ViT-G/14 (LiT)— when was it released?
It was published in November 2021. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
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.