YaART

Closed weights Yandex 2.3B parameters April 2024

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
Yandex
Organisation type
Industry
Country
Russia
Published
8 April 2024
Authors
Sergey Kastryulin, Artem Konev, Alexander Shishenya, Eugene Lyapustin, Artem Khurshudov, Alexander Tselousov, Nikita Vinokurov, Denis Kuznedelev, Alexander Markovich, Grigoriy Livshits, Alexey Kirillov, Anastasiia Tabisheva, Liubov Chubarova, Marina Kaminskaia, Alexander Ustyuzhanin, Artemii Shvetsov, Daniil Shlenskii, Valerii Startsev, Dmitrii Kornilov, Mikhail Romanov, Artem Babenko, Sergei Ovch…

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
2.3B
Training data
tokens
Batch size
4,800

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
8.2 × 10¹⁹ FLOP

There is cascade of 3 models: GEN64 Parameters: 2.3 billion Input: Textual prompt Output: 64x64 image Batch Size: 4800 Iterations: 1.1 × 10^6 Compute = 6 * 2.3 billion * 4800 * 1.1 × 10^6 = 7.2864e+19 SR256 Parameters: 700 million Input: 64x64 image Output: 256x256 image Batch Size: 960 Iterations: 1.5 × 10^6 Compute = 6 * 700 million * 960 * 1.5 × 10^6 = 6.048e+18 SR1024 Parameters: 700 million Input: 256x256 image Output: 1024x1024 image Batch Size: 512 Iterations: 1.5 × 10^6 Compute …

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
NVIDIA A100 SXM4 80 GB
Chips used
160
Power draw
126.5 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
API access
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
Speculative

Sources

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

Reference
YaART: Yet Another ART Rendering Technology
Last updated
28 November 2025

What the numbers mean

What this model is

YaART was published by Yandex, in Russia, in April 2024. It comes out of industry.

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 8.2 × 10¹⁹ FLOP of computation, on NVIDIA A100 SXM4 80 GB — a measure of what producing the model cost, not of how fast it answers.

Answers

YaART — common questions

01

What GPU do I need to run YaART?

None. YaART 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.

02

Is YaART open source?

No. YaART has not had its weights published, so it exists only as a service controlled by its owner.

03

How many parameters does YaART have?

YaART has 2.3B 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.

04

Who created YaART?

YaART was published by Yandex, based in Russia, categorised as industry.

05

When was YaART released?

YaART was published in April 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.

06

What is YaART used for?

YaART works in Image generation, and is recorded as handling text-to-image, Image generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

07

How much compute was used to train YaART?

Around 8.2 × 10¹⁹ FLOP, on NVIDIA A100 SXM4 80 GB. 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.

Source

Original publication

Record last updated 28 November 2025

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.