RQ-Transformer (LSUN-cat dataset)

Closed weights Kakao,POSTECH 612M 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
Image generation
Task
Text-to-image, Image generation

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
612M

612M from Table 5 - LSUN-cat row we provide details for LSUN-cat with largest compute

Training data
106,065,024 tokens

size of LSUN-cat

Epochs
200

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 × 10¹⁸ FLOP

"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. " we provide details for LSUN-cat with largest compute flops = (4) * (3.12e14) * (9*24 * 3600) * (0.3) = 2.9113344e+20 (num gpu) * (peak flops) * (time in seconds) * (assumed utilization rate)

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
864
Wall-clock time
216 hours (9 days)

9 days for LSUN-cat "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

About this model

RQ-Transformer (LSUN-cat dataset) was published by Kakao,POSTECH, in Korea (Republic of), in March 2022. The organisation is categorised as industry,Academia.

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

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

How it was trained

Training it took roughly 2.9 × 10¹⁸ FLOP of computation, on NVIDIA A100 — a measure of what producing the model cost, not of how fast it answers.

It was trained on about 106,065,024 tokens of text.

Answers

RQ-Transformer (LSUN-cat dataset) — common questions

01

How many parameters does RQ-Transformer (LSUN-cat dataset) have?

RQ-Transformer (LSUN-cat dataset) has 612M parameters. 612M from Table 5 - LSUN-cat row we provide details for LSUN-cat with largest compute. 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.

02

Who created RQ-Transformer (LSUN-cat dataset)?

RQ-Transformer (LSUN-cat dataset) was published by Kakao,POSTECH, based in Korea (Republic of), categorised as industry,Academia.

03

When was RQ-Transformer (LSUN-cat dataset) released?

RQ-Transformer (LSUN-cat 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.

04

What is RQ-Transformer (LSUN-cat dataset) used for?

RQ-Transformer (LSUN-cat dataset) works in Image generation, and is recorded as handling 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.

05

How much compute was used to train RQ-Transformer (LSUN-cat dataset)?

Around 2.9 × 10¹⁸ 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.

06

What GPU do I need to run RQ-Transformer (LSUN-cat dataset)?

None. RQ-Transformer (LSUN-cat 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.

07

Is RQ-Transformer (LSUN-cat dataset) open source?

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

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.