Flexi-JEST++
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 DeepMind
- Organisation type
- Industry
- Country
- United States of America
- Published
- 25 June 2024
- Authors
- Talfan Evans, Nikhil Parthasarathy, Hamza Merzic, Olivier J. Henaff
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Image classification
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
- 131,072,000,000,000 tokens
4b training examples seen (figure 1) The vision encoder takes images resized to (256 x 256) and the text-encoder tokenizes text with the sentencepiece tokenizer [26] trained on the English C4 dataset [39]. We crop the text to the first 64 tokens. visual encoder: ViT-B/16 4*10^9*((256/16)^2 + 64) = 1.28e+12 tokens (text and image)
Training compute
The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.
- Training compute
- 1.3 × 10²¹ FLOP
- How it was established
- Other
1.26*10^21 from the figure 1 there is slight disrepancy (within confidence interval) between sigclip/flexi-jest++ training compute ratio if we compare epoch's estimated compute and table 1
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 v5e
- Chips used
- 256
- Power draw
- 113.7 kW
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.
- Record confidence
- Confident
- Citations
- 30
Sources
Where this record came from and when it was last checked.
- Reference
- Data curation via joint example selection further accelerates multimodal learning
- Last updated
- 25 May 2026
What the numbers mean
Where it came from
Flexi-JEST++ was published by Google DeepMind, in United States of America, in June 2024. The organisation is categorised as industry.
It works in Vision, and is recorded as doing image classification.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
What went into building it
The training run consumed about 1.3 × 10²¹ FLOP, on Google TPU v5e. That figure describes the cost of creating it and has no bearing on how quickly it generates text.
The training set ran to roughly 131,072,000,000,000 tokens.
Answers
Flexi-JEST++ — common questions
What GPU do I need to run Flexi-JEST++?
None. Flexi-JEST++ 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.
Is Flexi-JEST++ open source?
No. Flexi-JEST++ has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does Flexi-JEST++ have?
No parameter count has been published for Flexi-JEST++, which is why no memory or speed figure appears on this page.
Who created Flexi-JEST++?
Flexi-JEST++ was published by Google DeepMind, based in United States of America, categorised as industry.
When was Flexi-JEST++ released?
Flexi-JEST++ was published in June 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is Flexi-JEST++ used for?
Flexi-JEST++ works in Vision, and is recorded as handling image classification. 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.
How much compute was used to train Flexi-JEST++?
Around 1.3 × 10²¹ FLOP, on Google TPU v5e. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.
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.