MusicGen TPS calculator

Open weights Meta AI 3.4B parameters June 2023

Each card below is assessed against this model at the context length and minimum quality you choose. Speed is an estimate for a single request, calculated from the card's memory bandwidth and the size of the model once compressed.

Calculated for this model

818 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla C1080

4 GB · Q6_K · 16.0 tok/s

Fastest card

B200

1,009 tok/s · 180 GB

Which GPUs can run MusicGen?

Set the inputs, read the answer

Context length tokens

A longer conversation needs more memory, which can push this model off smaller cards.

Minimum quality

Hides cards that would only fit the model by compressing it below this point.

Search cards

Card memory

Also show cards that cannot run it

818 cards match

Calculating

					Needs	Quantisation	Fit
1,009 tok/s 605–1,614 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	4.3 GB	Q8_0	Comfortable
1,009 tok/s 605–1,614 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	4.3 GB	Q8_0	Comfortable
805 tok/s 483–1,289 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	4.3 GB	Q8_0	Comfortable
805 tok/s 483–1,289 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	4.3 GB	Q8_0	Comfortable
644 tok/s 387–1,031 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	4.3 GB	Q8_0	Comfortable
617 tok/s 370–987 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	4.3 GB	Q8_0	Comfortable
617 tok/s 370–987 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	4.3 GB	Q8_0	Comfortable
590 tok/s 354–944 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	4.3 GB	Q8_0	Comfortable
524 tok/s 314–838 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	4.3 GB	Q8_0	Comfortable
524 tok/s 314–838 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	4.3 GB	Q8_0	Comfortable
524 tok/s 314–838 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	4.3 GB	Q8_0	Comfortable
497 tok/s 298–795 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	4.3 GB	Q8_0	Comfortable
424 tok/s 254–678 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	4.3 GB	Q8_0	Comfortable
424 tok/s 254–678 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	4.3 GB	Q8_0	Comfortable
424 tok/s 254–678 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	4.3 GB	Q8_0	Comfortable
424 tok/s 254–678 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	4.3 GB	Q8_0	Comfortable
424 tok/s 254–678 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	4.3 GB	Q8_0	Comfortable
323 tok/s 194–516 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	4.3 GB	Q8_0	Comfortable
323 tok/s 194–516 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	4.3 GB	Q8_0	Comfortable
269 tok/s 161–430 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	4.3 GB	Q8_0	Comfortable
263 tok/s 158–421 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	4.3 GB	Q8_0	Comfortable
257 tok/s 154–412 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	4.3 GB	Q8_0	Comfortable
257 tok/s 154–412 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	4.3 GB	Q8_0	Comfortable
257 tok/s 154–412 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	4.3 GB	Q8_0	Comfortable
257 tok/s 154–412 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	4.3 GB	Q8_0	Comfortable

Speeds are estimates for a single request — one conversation at a time — calculated from memory bandwidth, model size and quantisation. Real throughput varies with the inference runtime and its version. Figures published by hardware vendors measure many simultaneous requests and are much higher.

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: Meta AI
Organisation type: Industry
Country: United States of America
Published: 8 June 2023
Authors: Jade Copet, Felix Kreuk, Itai Gat, Tal Remez, David Kant, Gabriel Synnaeve, Yossi Adi, Alexandre Défossez

What it does

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

Domain: Audio
Task: Audio generation
Numerical format: FP16

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: 3.4B
Training data: 14,284,800,000,000 tokens

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: Open — downloadable
Model access: Open weights (non-commercial)
Training code: Open source

How it is classified

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

Foundation model: Yes
Likely above 10²³ FLOP: Yes
Why it is tracked: SOTA improvement
Record confidence: Likely
Citations: 665

Sources

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

Reference: Simple and Controllable Music Generation
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run MusicGen

Ranked by estimated tokens per second, newest card first where speeds tie. Because generation is bound by memory bandwidth, this ordering follows bandwidth rather than any gaming benchmark.

The smallest GPUs that still run MusicGen

The cheapest route in, by memory capacity. A tight fit runs the model but leaves nothing spare for a longer conversation.

What the numbers mean

Hardware requirements in practice

Minimum card

Tesla C1080

Memory needed

3.5 GB

Fastest

1,009 tok/s

MusicGen is small enough at 3.4B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The entry point is the Tesla C1080: 4 GB of memory, Q6_K compression, roughly 16.0 tokens per second.

The quickest result comes from a B200 at around 1,009 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

What this model is

MusicGen was published by Meta AI, in United States of America, in June 2023. industry is the category the publisher falls under.

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

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.

What decides the speed

Across every card that can run it, the middle of the range is about 32.0 tokens per second, and 779 of them clear the ten tokens per second that roughly matches reading speed.

Being dense, it reads all of itself per token, which is why the ordering by speed below follows the ordering by memory bandwidth so closely.

Its internal architecture is not on file, so memory is approximated from the parameter count and marked accordingly. Expect the real figure to differ, more so at long context.

What went into building it

Around 14,284,800,000,000 tokens went into training it.

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

Step by step

How to choose a GPU for MusicGen

The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.

01

Read the memory figure first

Every card here has been checked against MusicGen — around 3.5 GB at Q6_K. Capacity is the gate — a card either holds it or it does not.
02

Decide how long your conversations run

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for MusicGen.
03

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy of MusicGen — Q6_K on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Compare tokens per second, not specifications

Ranking by tokens per second for MusicGen follows memory bandwidth, not core counts, which is why the B200 tops it at 1,009 tok/s.
05

Check the fit verdict before buying

Tight means MusicGen loads and works, with no room to raise the context later. Comfortable means you can. The difference matters more than a few tokens per second.
06

See what else that card runs

Following a card through to its own page shows every other model it can hold, which is the question that follows once MusicGen is settled.

Answers

MusicGen — common questions

Can I run MusicGen on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 4.3 GB and generating roughly 169 tokens per second — a comfortable fit.

Is MusicGen open source?

Its weights are published, so MusicGen can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.

How many parameters does MusicGen have?

MusicGen has 3.4B parameters. "We train autoregressive transformer models at different sizes: 300M, 1.5B, 3.3B parameters" Uses EnCodec 32kHz (HF version has 59M params) for audio tokenization. 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.

Who created MusicGen?

MusicGen was published by Meta AI, based in United States of America, categorised as industry.

When was MusicGen released?

MusicGen was published in June 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.

What is MusicGen used for?

MusicGen works in Audio, and is recorded as handling audio generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download MusicGen?

The weights for MusicGen are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

Can I run MusicGen if it does not fit in my GPU?

Partly. Layers that do not fit sit in system memory and run at a fraction of the speed, so a mostly-offloaded MusicGen is rarely worth using. Every figure here assumes the whole model is on the card.

Would two GPUs run MusicGen faster?

A second card roughly doubles the memory available but not the generation rate. With 818 cards already able to run MusicGen alone, the case for pairing is weak.

Why does the quantisation differ between cards for MusicGen?

Because capacity varies, so does how hard MusicGen has to be squeezed — 2 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these MusicGen speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked. That is why each is published as a range such as 605–1,614 tok/s on the B200 rather than a single number.

What GPU do I need to run MusicGen?

The smallest card in our catalogue that holds MusicGen is the Tesla C1080, with 4 GB of memory. It runs the model at Q6_K using about 3.5 GB, and produces roughly 16.0 tokens per second. 818 cards in total can run it.

How fast is MusicGen on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 1,009 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 779 of the cards that can run MusicGen clear that.

How much VRAM does MusicGen need?

About 3.5 GB at Q6_K compression, which is what the smallest card that runs it uses. Less compression needs more: the figures in the memory column above are recalculated for each card, because each one holds the least-compressed version it can.

Can I run MusicGen on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 4.3 GB and generating roughly 188 tokens per second — a comfortable fit.

Can I run MusicGen on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 4.3 GB and generating roughly 115 tokens per second — a comfortable fit.

Can I run MusicGen on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 4.3 GB and generating roughly 142 tokens per second — a comfortable fit.

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.

All AI models