RQ-Transformer (3.8B params ImageNet dataset)

Closed weights Kakao,POSTECH 3.8B parameters March 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
Kakao,POSTECH
Organisation type
Industry,Academia
Country
Korea (Republic of)
Published
3 March 2022
Authors
Doyup Lee, Chiheon Kim, Saehoon Kim, Minsu Cho, Wook-Shin Han

What it does

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

Domain
Vision, Image generation
Task
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.

Parameters
3.8B

3822M from Table 5 - ImageNet rows

Training data
327,680,000 tokens

size of ImageNet

Epochs
50

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
2.9 × 10²⁰ FLOP

"We use eight NVIDIA A100 GPUs to train RQ-Transformer of 1.4B parameters, and four GPUs to train RQ-Transformers of other sizes. The training time is <9 days for LSUN-cat, LSUN-bedroom, <4.5 days for ImageNet, and CC-3M, and <1 day for LSUN-church and FFHQ. " Taken literally, suggests 3.8B model used fewer GPUs than 1.4B. This seems likely to be a typo, so I assume details are meant to be given for largest model (3.8B). (8) * (3.12e14) * (4.5 * 24 * 3600) * (0.3) = 2.911e20 (num gpu) * (peak …

How it was established
Hardware

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
NVIDIA A100
Chips used
4
Chip-hours
432
Wall-clock time
108 hours

States 4.5 days for ImageNet for 1.4B model, but this is probably a typo. I expect these details were given for the largest model. "We use eight NVIDIA A100 GPUs to train RQ-Transformer of 1.4B parameters, and four GPUs to trainRQ-Transformers of other sizes. The training time is <9 days for LSUN-cat, LSUN-bedroom, <4.5 days for ImageNet, and CC-3M, and <1 day for LSUN-church and FFHQ. "

Power draw
3.2 kW

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
763

Sources

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

Reference
Autoregressive Image Generation using Residual Quantization
Last updated
25 May 2026

What the numbers mean

What this model is

RQ-Transformer (3.8B params ImageNet dataset) was published by Kakao,POSTECH, in Korea (Republic of), in March 2022. industry,Academia is the category the publisher falls under.

It works in Vision, Image generation, and is recorded as doing text-to-image.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

Training and provenance

Training it took roughly 2.9 × 10²⁰ FLOP of computation, on NVIDIA A100 — a measure of what producing the model cost, not of how fast it answers.

The training set ran to roughly 327,680,000 tokens.

Answers

RQ-Transformer (3.8B params ImageNet dataset) — common questions

01

When was RQ-Transformer (3.8B params ImageNet dataset) released?

RQ-Transformer (3.8B params ImageNet dataset) was published in March 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

What is RQ-Transformer (3.8B params ImageNet dataset) used for?

RQ-Transformer (3.8B params ImageNet dataset) works in Vision, Image generation, and is recorded as handling text-to-image. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

03

How much compute was used to train RQ-Transformer (3.8B params ImageNet dataset)?

Around 2.9 × 10²⁰ FLOP, on NVIDIA A100. 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

What GPU do I need to run RQ-Transformer (3.8B params ImageNet dataset)?

None. RQ-Transformer (3.8B params ImageNet dataset) 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

Is RQ-Transformer (3.8B params ImageNet dataset) open source?

The licensing for RQ-Transformer (3.8B params ImageNet dataset) was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

06

How many parameters does RQ-Transformer (3.8B params ImageNet dataset) have?

RQ-Transformer (3.8B params ImageNet dataset) has 3.8B parameters. 3822M from Table 5 - ImageNet rows. 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

Who created RQ-Transformer (3.8B params ImageNet dataset)?

RQ-Transformer (3.8B params ImageNet dataset) was published by Kakao,POSTECH, based in Korea (Republic of), categorised as industry,Academia.

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.