GPT-2-Small+Pixelfly

Closed weights Stanford University,SambaNova Systems, Inc,Peking University,Adobe,University at Buffalo 68M parameters November 2021

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
Stanford University,SambaNova Systems, Inc,Peking University,Adobe,University at Buffalo
Organisation type
Academia,Industry,Academia,Industry,Academia
Country
United States of America, China
Published
30 November 2021
Authors
Tri Dao, Beidi Chen, Kaizhao Liang, Jiaming Yang, Zhao Song, Atri Rudra, Christopher Ré

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
68M

Table 6

Training data
103,000,000 tokens
Epochs
100

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
4.2 × 10¹⁸ FLOP

Using 6ND: 6*68000000*103000000 tokens*100 epochs=4.2024e+18

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

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 source

Apache for code: https://github.com/HazyResearch/fly

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
94
Benchmark data
GPT-2-Small+Pixelfly

Sources

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

Reference
Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models
Last updated
25 May 2026

What the numbers mean

What this model is

GPT-2-Small+Pixelfly was published by Stanford University,SambaNova Systems, Inc,Peking University,Adobe,University at Buffalo, in United States of America, in November 2021. academia,Industry,Academia,Industry,Academia is the category the publisher falls under.

It works in Language, and is recorded as doing language modeling.

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

The training run consumed about 4.2 × 10¹⁸ FLOP, on NVIDIA V100. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

It was trained on about 103,000,000 tokens of text.

Answers

GPT-2-Small+Pixelfly — common questions

01

Is GPT-2-Small+Pixelfly open source?

No. GPT-2-Small+Pixelfly has not had its weights published, so it exists only as a service controlled by its owner.

02

How many parameters does GPT-2-Small+Pixelfly have?

GPT-2-Small+Pixelfly has 68M parameters. Table 6. 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.

03

Who created GPT-2-Small+Pixelfly?

GPT-2-Small+Pixelfly was published by Stanford University,SambaNova Systems, Inc,Peking University,Adobe,University at Buffalo, based in United States of America, categorised as academia,Industry,Academia,Industry,Academia.

04

When was GPT-2-Small+Pixelfly released?

GPT-2-Small+Pixelfly was published in November 2021. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

05

What is GPT-2-Small+Pixelfly used for?

GPT-2-Small+Pixelfly works in Language, and is recorded as handling language modeling. 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.

06

How much compute was used to train GPT-2-Small+Pixelfly?

Around 4.2 × 10¹⁸ FLOP, on 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.

07

What GPU do I need to run GPT-2-Small+Pixelfly?

None. GPT-2-Small+Pixelfly 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.

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.