GPT-3 XL

Closed weights OpenAI 1.3B parameters June 2020

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
22 June 2020
Authors
Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, C…

What it does

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

Domain
Language
Task
Text autocompletion, Language modeling/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
1.3B

1.3B

Training data
300,000,000,000 tokens

300b, per table d.1

Batch size
1,000,000

1M, per table 2.1

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
2.4 × 10²¹ FLOP

Table D.1 https://arxiv.org/abs/2005.14165

How it was established
Reported

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 Tesla V100 DGXS 32 GB
Cloud vendor
Microsoft

How it is classified

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

Record confidence
Confident
Citations
58,240

Sources

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

Reference
Language Models are Few-Shot Learners
Last updated
25 May 2026

What the numbers mean

Background

GPT-3 XL was published by OpenAI, in United States of America, in June 2020. It comes out of industry.

It works in Language, and is recorded as doing text autocompletion, Language modeling/generation.

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

What went into building it

Training it took roughly 2.4 × 10²¹ FLOP of computation, on NVIDIA Tesla V100 DGXS 32 GB — a measure of what producing the model cost, not of how fast it answers.

Around 300,000,000,000 tokens went into training it.

Answers

GPT-3 XL — common questions

01

What is GPT-3 XL used for?

GPT-3 XL works in Language, and is recorded as handling text autocompletion, Language modeling/generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

02

How much compute was used to train GPT-3 XL?

Around 2.4 × 10²¹ FLOP, on NVIDIA Tesla V100 DGXS 32 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.

03

What GPU do I need to run GPT-3 XL?

None. GPT-3 XL 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.

04

Is GPT-3 XL open source?

The licensing for GPT-3 XL was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

05

How many parameters does GPT-3 XL have?

GPT-3 XL has 1.3B parameters. 1.3B. 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.

06

Who created GPT-3 XL?

GPT-3 XL was published by OpenAI, based in United States of America, categorised as industry.

07

When was GPT-3 XL released?

GPT-3 XL was published in June 2020. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

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.