Monarch-GPT-2-Small

Closed weights Stanford University,University at Buffalo,University of Michigan 72M parameters April 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
Stanford University,University at Buffalo,University of Michigan
Organisation type
Academia,Academia,Academia
Country
United States of America
Published
1 April 2022
Authors
Tri Dao, Beidi Chen, Nimit Sohoni, Arjun Desai, Michael Poli, Jessica Grogan, Alexander Liu, Aniruddh Rao, 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
72M

GPPT-2 small has 124M parameters: https://huggingface.co/openai-community/gpt2 upd see Table 2

Training data
103,000,000 tokens

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
9 × 10¹⁹ FLOP

400k iterations with batch size 512 (Appendix E) GPT 2 small on Huggingface has a context length of 1024 FLOP estimate using 6ND: 6*400000*512*1024*72000000=9.0596966e+19

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/tree/master https://github.com/HazyResearch/fly/tree/master/configs/model/gpt2model

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
130
Benchmark data
Monarch-GPT-2-Small

Sources

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

Reference
Monarch: Expressive Structured Matrices for Efficient and Accurate Training
Last updated
25 May 2026

What the numbers mean

About this model

Monarch-GPT-2-Small was published by Stanford University,University at Buffalo,University of Michigan, in United States of America, in April 2022. academia,Academia,Academia is the category the publisher falls under.

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

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

Training and provenance

Training it took roughly 9 × 10¹⁹ FLOP of computation, on NVIDIA V100 — a measure of what producing the model cost, not of how fast it answers.

Around 103,000,000 tokens went into training it.

Answers

Monarch-GPT-2-Small — common questions

01

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

None. Monarch-GPT-2-Small 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 Monarch-GPT-2-Small open source?

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

03

How many parameters does Monarch-GPT-2-Small have?

Monarch-GPT-2-Small has 72M parameters. GPPT-2 small has 124M parameters: https://huggingface.co/openai-community/gpt2 upd see Table 2. 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 Monarch-GPT-2-Small?

Monarch-GPT-2-Small was published by Stanford University,University at Buffalo,University of Michigan, based in United States of America, categorised as academia,Academia,Academia.

05

When was Monarch-GPT-2-Small released?

Monarch-GPT-2-Small was published in April 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.

06

What is Monarch-GPT-2-Small used for?

Monarch-GPT-2-Small works in Language, and is recorded as handling language modeling. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

07

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

Around 9 × 10¹⁹ 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.

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.