Suno Bark Model TPS calculator

Open weights Suno 300M parameters April 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 · Q8_0 · 123 tok/s

Fastest card

B200

11,294 tok/s · 180 GB

Which GPUs can run Suno Bark Model?

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
11,294 tok/s 6,776–18,071 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	1.0 GB	Q8_0	Comfortable
11,294 tok/s 6,776–18,071 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	1.0 GB	Q8_0	Comfortable
9,019 tok/s 5,411–14,430 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	1.0 GB	Q8_0	Comfortable
9,019 tok/s 5,411–14,430 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	1.0 GB	Q8_0	Comfortable
7,213 tok/s 4,328–11,540 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	1.0 GB	Q8_0	Comfortable
6,904 tok/s 4,142–11,046 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.0 GB	Q8_0	Comfortable
6,904 tok/s 4,142–11,046 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.0 GB	Q8_0	Comfortable
6,607 tok/s 3,964–10,571 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	1.0 GB	Q8_0	Comfortable
5,864 tok/s 3,518–9,382 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	1.0 GB	Q8_0	Comfortable
5,864 tok/s 3,518–9,382 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	1.0 GB	Q8_0	Comfortable
5,864 tok/s 3,518–9,382 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	1.0 GB	Q8_0	Comfortable
5,562 tok/s 3,337–8,900 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	1.0 GB	Q8_0	Comfortable
4,744 tok/s 2,846–7,590 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.0 GB	Q8_0	Comfortable
4,744 tok/s 2,846–7,590 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	1.0 GB	Q8_0	Comfortable
4,744 tok/s 2,846–7,590 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	1.0 GB	Q8_0	Comfortable
4,744 tok/s 2,846–7,590 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.0 GB	Q8_0	Comfortable
4,744 tok/s 2,846–7,590 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	1.0 GB	Q8_0	Comfortable
3,612 tok/s 2,167–5,779 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	1.0 GB	Q8_0	Comfortable
3,612 tok/s 2,167–5,779 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	1.0 GB	Q8_0	Comfortable
3,010 tok/s 1,806–4,816 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	1.0 GB	Q8_0	Comfortable
2,946 tok/s 1,767–4,713 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	1.0 GB	Q8_0	Comfortable
2,880 tok/s 1,728–4,608 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	1.0 GB	Q8_0	Comfortable
2,880 tok/s 1,728–4,608 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	1.0 GB	Q8_0	Comfortable
2,880 tok/s 1,728–4,608 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	1.0 GB	Q8_0	Comfortable
2,880 tok/s 1,728–4,608 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	1.0 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: Suno
Organisation type: Industry
Country: United States of America
Published: 15 April 2023

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: 300M
Training data: 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: Unreleased
Hugging Face: suno

How it is classified

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

Record confidence: Confident

Sources

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

Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Suno Bark Model

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 Suno Bark Model

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

What it takes to run this model

Minimum card

Tesla C1080

Memory needed

1.0 GB

Fastest

11,294 tok/s

Suno Bark Model reaches a parameter count of 300M. That is small enough that hardware is rarely the obstacle, including on cards several years old. The number of cards we track that can run it: 818.

The smallest card that holds it is Tesla C1080, with a memory capacity of 4 GB, running it at a compression of Q8_0 and producing around 123 tokens per second.

At the other end sits B200, generating roughly 11,294 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

What this model is

Suno Bark Model was published by Suno, in the country recorded as United States of America, during April 2023. It comes out of an organisation categorised as industry.

It works in the domain of Audio, and is recorded as performing the task of audio generation.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached. On Hugging Face it is published under the organisation suno.

What decides the speed

The median result is around 317.1 tokens per second. Exceeding reading speed outright: 818 of them.

Every weight participates in every token here, so bandwidth is the whole story: the ranking below is effectively a ranking of memory throughput.

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.

Step by step

How to choose a GPU for Suno Bark Model

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

01

Start from the memory column

Every card here has been checked against Suno Bark Model, needing around 1.0 GB at a compression of Q8_0. No amount of processing power compensates for a card that cannot hold it.
02

Set the context length you will work at

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect, because at long context a card that handles short questions easily can be dropped by Suno Bark Model.
03

Set a quality floor

Compression is what makes a model fit smaller cards, at some cost in accuracy, reaching a compression of Q8_0 on the smallest card that fits. Setting a minimum quality drops the cards that only manage it by squeezing further than you would want, and holds the comparison at one level.
04

Sort by speed

Ranking by tokens per second follows memory bandwidth rather than core counts, for Suno Bark Model. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 11,294 tok/s.
05

Check the fit verdict before buying

Tight means it loads and works with no room to raise the context later, in the case of Suno Bark Model. Comfortable means you can grow the context later. That difference matters more than a few tokens per second, so buy for comfortable if you expect to.
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 you have settled on Suno Bark Model.

Answers

Suno Bark Model — common questions

Suno Bark Model— can I run it on a GPU holding 16 GB?

Yes. The card Tesla V100 SXM2 16 GB, holding 16 GB, runs it at a compression of Q8_0, using about 1.0 GB and generating roughly 1,595 tokens per second. The fit is comfortable.

Suno Bark Model— can I run it on a GPU holding 24 GB?

Yes. The card GeForce RTX 5090 D V2, holding 24 GB, runs it at a compression of Q8_0, using about 1.0 GB and generating roughly 1,892 tokens per second. The fit is comfortable.

Suno Bark Model— is it open source?

Its weights are published, so it 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.

Suno Bark Model— how many parameters does it have?

It has a parameter count of 300M. 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.

Suno Bark Model— who created it?

It was published by Suno, based in United States of America, an organisation categorised as industry.

Suno Bark Model— when was it released?

It was published in April 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.

Suno Bark Model— what is it used for?

It works in the domain of Audio, and is recorded as handling the task of audio generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Suno Bark Model— where can I download it?

Its weights are published on Hugging Face, under the organisation suno. We do not host model files — this site calculates what hardware is needed to run them.

Suno Bark Model— can I run it if it does not fit in my GPU?

It can be split between the card and system memory, but it generates painfully slowly that way. Every figure here assumes the whole model is resident on the card.

Suno Bark Model— would two GPUs run it faster?

Two cards buy memory rather than speed, which matters only if one card cannot hold it. The number that can: 818. So a second card is rarely the answer here.

Suno Bark Model— why does the quantisation differ between cards?

Each card is shown running the least-compressed copy it can hold. The number of distinct compression levels across the cards that fit it: 1. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Suno Bark Model— how accurate are these speed estimates?

These are estimates with real error bars, and any of them could reasonably land anywhere in its published range depending on which runtime you use. The fastest result here: 6,776–18,071 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Suno Bark Model— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Tesla C1080, with a memory capacity of 4 GB. It runs the model at a compression of Q8_0 using about 1.0 GB, and produces roughly 123 tokens per second. The number of cards able to run it in total: 818.

Suno Bark Model— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 11,294 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and the number of cards clearing that: 818.

Suno Bark Model— how much VRAM does it need?

It needs about 1.0 GB at a compression of Q8_0, 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.

Suno Bark Model— can I run it on a GPU holding 8 GB?

Yes. The card CMP 170HX 8 GB, holding 8 GB, runs it at a compression of Q8_0, using about 1.0 GB and generating roughly 2,104 tokens per second. The fit is comfortable.

Suno Bark Model— can I run it on a GPU holding 12 GB?

Yes. The card GeForce RTX 3080 Ti, holding 12 GB, runs it at a compression of Q8_0, using about 1.0 GB and generating roughly 1,288 tokens per second. The fit is comfortable.

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.

All AI models