MusicLM

Closed weights Google 860M parameters January 2023

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
Google
Organisation type
Industry
Country
United States of America
Published
26 January 2023
Authors
Andrea Agostinelli, Timo I. Denk, Zalán Borsos, Jesse Engel, Mauro Verzetti, Antoine Caillon, Qingqing Huang, Aren Jansen, Adam Roberts, Marco Tagliasacchi, Matt Sharifi, Neil Zeghidour, Christian Frank

What it does

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

Domain
Audio
Task
Audio generation
Base model
W2v-BERT

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
860M

"We use decoder-only Transformers for modeling the semantic stage and the acoustic stages of AudioLM. The models share the same architecture, composed of 24 layers, 16 attention heads, an embedding dimension of 1024, feed-forward layers of dimensionality 4096, dropout of 0.1, and relative positional embeddings (Raffel et al., 2020), resulting in 430M parameters per stage." "stage" seems to mean semantic + acoustic, so 860M total

Training data
tokens

>280k hours

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
Unreleased

How it is classified

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

Foundation model
Yes
Why it is tracked
SOTA improvement

"We demonstrate that our method outperforms baselines on MusicCaps, a hand-curated, high-quality dataset of 5.5k music-text pairs prepared by musicians."

Record confidence
Confident
Citations
671

Sources

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

Reference
MusicLM: Generating Music From Text
Last updated
25 May 2026

What the numbers mean

What this model is

MusicLM was published by Google, in United States of America, in January 2023. It comes out of industry.

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

It is derived from W2v-BERT rather than trained from scratch, which is the usual way a specialised model is produced.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

How it was trained

It is tracked in the underlying dataset for one reason in particular: sOTA improvement.

Answers

MusicLM — common questions

01

How many parameters does MusicLM have?

MusicLM has 860M parameters. "We use decoder-only Transformers for modeling the semantic stage and the acoustic stages of AudioLM. The models share the same architecture, composed of 24 layers, 16 attention heads, an embedding dimension of 1024, feed-forward layers of dimensionality 4096, dropout of 0.1, and relative positional embeddings (Raffel et al., 2020), resulting in 430M parameters per stage." "stage" seems to mean semantic + acoustic, so 860M total. 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.

02

Who created MusicLM?

MusicLM was published by Google, based in United States of America, categorised as industry.

03

When was MusicLM released?

MusicLM was published in January 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

04

What is MusicLM used for?

MusicLM works in Audio, and is recorded as handling audio generation. 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.

05

What GPU do I need to run MusicLM?

None. MusicLM 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.

06

Is MusicLM open source?

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

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.