Sparse Transformer (Enwik8)

Closed weights OpenAI 95M parameters April 2019

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
OpenAI
Organisation type
Industry
Country
United States of America
Published
23 April 2019
Authors
Rewon Child, Scott Gray, Alec Radford, Ilya Sutskever

What it does

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

Domain
Language
Task
Language modeling

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
95M

95M

Training data
90,000,000 tokens

[tokens] " We trained with a context length of 12,288, which is longer than previous approaches. We trained on the first 90 million tokens and reserved the last 10 million for validation and test"

Epochs
80

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
4.1 × 10¹⁸ FLOP

6 FLOP / token / parameter * 95000000 parameters * 90000000 tokens * 80 epochs = 4.104e+18 FLOP

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 V100
Chips used
8
Power draw
4.9 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
Open (non-commercial)

some primitives are released here, but not the entire training code: https://github.com/openai/sparse_attention no clear license "Normally, implementing sparse attention would involve slicing query and key matrices in blocks, so to ease experimentation we implemented a set of block-sparse kernels⁠ which efficiently perform these operations on the the GPU. We open-source these kernels and provide example sparse attention functions in this repository⁠(opens in a new window)."

How it is classified

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

Record confidence
Confident

Sources

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

Reference
Generating Long Sequences with Sparse Transformers
Last updated
11 February 2026

What the numbers mean

Background

Sparse Transformer (Enwik8) was published by OpenAI, in the country recorded as United States of America, during April 2019. The category the publisher falls under is industry.

It works in the domain of Language, and is recorded as performing the task of language modeling.

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

How it was trained

The training run consumed about 4.1 × 10¹⁸ FLOP, on hardware recorded as NVIDIA V100. That figure measures what producing the model cost, and has no bearing on how fast it answers.

It was trained on a corpus of about 90,000,000 tokens of text.

Answers

Sparse Transformer (Enwik8) — common questions

01

Sparse Transformer (Enwik8)— 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.

02

Sparse Transformer (Enwik8)— is it open source?

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

03

Sparse Transformer (Enwik8)— how many parameters does it have?

It has a parameter count of 95M. 95M. 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

Sparse Transformer (Enwik8)— who created it?

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

05

Sparse Transformer (Enwik8)— when was it released?

It was published in April 2019. 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

Sparse Transformer (Enwik8)— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

07

Sparse Transformer (Enwik8)— how much compute was used to train it?

Training consumed around 4.1 × 10¹⁸ FLOP, on hardware recorded as NVIDIA V100. 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 11 February 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.