Parti

Closed weights Google Research 20B parameters June 2022

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
22 June 2022
Authors
Jiahui Yu, Yuanzhong Xu, Jing Yu Koh, Thang Luong, Gunjan Baid, Zirui Wang, Vijay Vasudevan, Alexander Ku, Yinfei Yang, Burcu Karagol Ayan, Ben Hutchinson, Wei Han, Zarana Parekh, Xin Li, Han Zhang, Jason Baldridge, Yonghui Wu

What it does

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

Domain
Image generation
Task
Text-to-image, Image generation
Approach
Self-supervised learning
Numerical format
BF16

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
20B

Abstract: "we achieve consistent quality improvements by scaling the encoder-decoder Transformer model up to 20B parameters"

Training data
4,718,592,000,000 tokens

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
5.1 × 10²³ FLOP

Calculated from architecture. Does not take into account the encoding and decoding of text and images, only the transformer stack. Table 1 shows for the 20B model 16 encoder layers 64 decoder layers Dmodel = 4096 Dhidden = 16384 Num heads = 64 Just below table 1: "We use a maximum length of text tokens of 128, and the length of image tokens are fixed to 1024" I take the length of the sequence to be 100 for the encoder stack and 1024 for the decoder stack. Section 3, Training: "a total of 450…

How it was established
Operation counting

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 v4
Compute cost
$427,179

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

"For these reasons, we have decided not to release our Parti models, code, or data for public use without further safeguards in place" https://sites.research.google/parti/

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Foundation model
Yes
Likely above 10²³ FLOP
Yes
Why it is tracked
SOTA improvement

"Second, we achieve consistent quality improvements by scaling the encoder-decoder Transformer model up to 20B parameters, with a new state-of-the-art zero-shot FID score of 7.23 and finetuned FID score of 3.22 on MS-COCO"

Record confidence
Confident
Citations
1,476

Sources

Where this record came from and when it was last checked.

Reference
Scaling Autoregressive Models for Content-Rich Text-to-Image Generation
Last updated
25 May 2026

What the numbers mean

Where it came from

Parti was published by Google Research, in the country recorded as United States of America, during June 2022. The category the publisher falls under is industry.

It works in the domain of Image generation, and is recorded as performing the task of text-to-image, Image generation.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

Training and provenance

Training it took a computation budget of roughly 5.1 × 10²³ FLOP, on hardware recorded as Google TPU v4. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Training consumed a corpus of around 4,718,592,000,000 tokens of text.

Its inclusion criterion: sOTA improvement.

Answers

Parti — common questions

01

Parti— when was it released?

It was published in June 2022. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

02

Parti— what is it used for?

It works in the domain of Image generation, and is recorded as handling the task of text-to-image, Image 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.

03

Parti— how much compute was used to train it?

Training consumed around 5.1 × 10²³ FLOP, on hardware recorded as Google TPU v4. 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.

04

Parti— 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.

05

Parti— is it open source?

No. Its weights have not been published, so it exists only as a service controlled by its owner.

06

Parti— how many parameters does it have?

It has a parameter count of 20B. Abstract: "we achieve consistent quality improvements by scaling the encoder-decoder Transformer model up to 20B parameters". 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.

07

Parti— who created it?

It was published by Google Research, based in United States of America, an organisation categorised as industry.

Source

Original publication

Record last updated 25 May 2026

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.