MuseNet

Closed weights OpenAI 2B 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
25 April 2019
Authors
OpenAI

What it does

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

Domain
Audio
Task
Audio 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
2B

From article: 72 Layers 24 Attention heads Assumptions: D_head = 64 (GPT-2) D_model = 24*64=1536 (based on D_head) D_mlp = 4*1536=6144 Attention: H*(W*(2*D+N)+N*M) 24*(1536*(2*64+64)+64*1536)=9437184 MLP: 1536*6144+6144*1536=18874368 Total parameters: 72*(9437184+18874368)=2038431744

Training data
tokens

“hundreds of thousands of MIDI files”

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
2.2 × 10²⁰ FLOP

From article: 72 Layers 24 Attention heads 4096 ctx length Assumptions: D_head = 64 (GPT-2) D_model = 24*64=1536 (based on D_head) D_mlp = 4*1536=6144 Average sequence length: 5000 Epochs: 5 Training data: 500000 Forward FLOP: Attention: 2*H*(W*(2*D+N)+L*(D+N)+N*M) 2*24*(1536*(2*64+64)+4096*(64+64)+64*1536)=44040192 MLP: 2*(1536*6144+6144*1536)=37748736 Total forward flop: 72*(44040192+37748736)=5888802816 Training compute 5888802816*3*500000*5000*5=220830105600000000000=2.2e20

How it was established
Operation counting

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

How it is classified

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

Why it is tracked
Significant use
Record confidence
Likely

Sources

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

Reference
MuseNet
Last updated
28 November 2025

What the numbers mean

Where it came from

MuseNet was published by OpenAI, in United States of America, in April 2019. The organisation is categorised as industry.

It works in Audio, and is recorded as doing audio generation.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

What went into building it

The training run consumed about 2.2 × 10²⁰ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

The reason it appears in this catalogue at all is significant use.

Answers

MuseNet — common questions

01

What is MuseNet used for?

MuseNet works in Audio, and is recorded as handling audio 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 MuseNet?

Around 2.2 × 10²⁰ FLOP. 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 MuseNet?

None. MuseNet 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 MuseNet open source?

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

05

How many parameters does MuseNet have?

MuseNet has 2B parameters. From article: 72 Layers 24 Attention heads Assumptions: D_head = 64 (GPT-2) D_model = 24*64=1536 (based on D_head) D_mlp = 4*1536=6144 Attention: H*(W*(2*D+N)+N*M) 24*(1536*(2*64+64)+64*1536)=9437184 MLP: 1536*6144+6144*1536=18874368 Total parameters: 72*(9437184+18874368)=2038431744. 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 MuseNet?

MuseNet was published by OpenAI, based in United States of America, categorised as industry.

07

When was MuseNet released?

MuseNet 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.

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.