Wuerstchen TPS calculator

Open weights Technische Hochschule Ingolstadt,University of Montreal / Université de Montréal,Mila - Quebec AI (originally Montreal Institute for Learning Algorithms),Polytechnique Montreal,Wand Technologies 1B parameters September 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 · 36.9 tok/s

Fastest card

B200

3,388 tok/s · 180 GB

Which GPUs can run Wuerstchen?

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
3,388 tok/s 2,033–5,421 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	1.8 GB	Q8_0	Comfortable
3,388 tok/s 2,033–5,421 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	1.8 GB	Q8_0	Comfortable
2,706 tok/s 1,623–4,329 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	1.8 GB	Q8_0	Comfortable
2,706 tok/s 1,623–4,329 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	1.8 GB	Q8_0	Comfortable
2,164 tok/s 1,298–3,462 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	1.8 GB	Q8_0	Comfortable
2,071 tok/s 1,243–3,314 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.8 GB	Q8_0	Comfortable
2,071 tok/s 1,243–3,314 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	1.8 GB	Q8_0	Comfortable
1,982 tok/s 1,189–3,171 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	1.8 GB	Q8_0	Comfortable
1,759 tok/s 1,055–2,815 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	1.8 GB	Q8_0	Comfortable
1,759 tok/s 1,055–2,815 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	1.8 GB	Q8_0	Comfortable
1,759 tok/s 1,055–2,815 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	1.8 GB	Q8_0	Comfortable
1,669 tok/s 1,001–2,670 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	1.8 GB	Q8_0	Comfortable
1,423 tok/s 854–2,277 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.8 GB	Q8_0	Comfortable
1,423 tok/s 854–2,277 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	1.8 GB	Q8_0	Comfortable
1,423 tok/s 854–2,277 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	1.8 GB	Q8_0	Comfortable
1,423 tok/s 854–2,277 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	1.8 GB	Q8_0	Comfortable
1,423 tok/s 854–2,277 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	1.8 GB	Q8_0	Comfortable
1,084 tok/s 650–1,734 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	1.8 GB	Q8_0	Comfortable
1,084 tok/s 650–1,734 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	1.8 GB	Q8_0	Comfortable
903 tok/s 542–1,445 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	1.8 GB	Q8_0	Comfortable
884 tok/s 530–1,414 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	1.8 GB	Q8_0	Comfortable
864 tok/s 518–1,382 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	1.8 GB	Q8_0	Comfortable
864 tok/s 518–1,382 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	1.8 GB	Q8_0	Comfortable
864 tok/s 518–1,382 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	1.8 GB	Q8_0	Comfortable
864 tok/s 518–1,382 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	1.8 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: Technische Hochschule Ingolstadt,University of Montreal / Université de Montréal,Mila - Quebec AI (originally Montreal Institute for Learning Algorithms),Polytechnique Montreal,Wand Technologies
Organisation type: Academia,Academia,Academia,Academia,Industry
Country: Germany, Canada, United States of America
Published: 29 September 2023
Authors: Pablo Pernias, Dominic Rampas, Mats L. Richter, Christopher J. Pal, Marc Aubreville

What it does

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

Domain: Image generation
Task: Text-to-image, Image 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: 1B
Training data: 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: 8.3 × 10²¹ FLOP
How it was established: Hardware

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 (unrestricted)
Hugging Face: dome272

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.

Reference: Wuerstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Wuerstchen

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 Wuerstchen

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 you need to run it

Minimum card

Tesla C1080

Memory needed

1.8 GB

Fastest

3,388 tok/s

Wuerstchen is small enough at 1B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

The least hardware that works is a Tesla C1080. Its 4 GB is enough at Q8_0 compression, giving roughly 36.9 tokens per second.

A B200 is the fastest we calculate for it: about 3,388 tokens per second, from 8,000 GB/s of memory bandwidth.

Background

Wuerstchen was published by Technische Hochschule Ingolstadt,University of Montreal / Université de Montréal,Mila - Quebec AI (originally Montreal Institute for Learning Algorithms),Polytechnique Montreal,Wand Technologies, in Germany, in September 2023. The organisation is categorised as academia,Academia,Academia,Academia,Industry.

It works in Image generation, and is recorded as doing text-to-image, Image generation.

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded. It is published under the dome272 organisation on Hugging Face.

Reading the throughput figures

Across every card that can run it, the middle of the range is about 95.1 tokens per second, and 806 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.

Without the attention layout on record, the memory column is an approximation. It is close enough to choose hardware by, and least reliable at long context.

What went into building it

Training it took roughly 8.3 × 10²¹ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.

Step by step

How to choose a GPU for Wuerstchen

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

Look at what Wuerstchen actually needs — around 1.8 GB at Q8_0. No amount of processing power compensates for a card that cannot hold it.
02

Decide how long your conversations run

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason Wuerstchen stops fitting a card that seemed fine.
03

Decide how much compression you will accept

Compression is what makes Wuerstchen fit smaller cards, at some cost in accuracy — Q8_0 on the smallest card that fits. A minimum quality removes the ones that go too far.
04

Rank by throughput rather than spec sheet

The speed ordering for Wuerstchen is effectively an ordering by memory bandwidth, which is why the B200 tops it at 3,388 tok/s.
05

Read the fit column last

The fit column separates cards that just manage Wuerstchen from those with room to spare. Buy for the second if the context might grow.
06

Check the card from the other side

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond Wuerstchen.

Answers

Wuerstchen — common questions

How fast is Wuerstchen on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 3,388 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 806 of the cards that can run Wuerstchen clear that.

How much VRAM does Wuerstchen need?

About 1.8 GB at Q8_0 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 Wuerstchen on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 1.8 GB and generating roughly 631 tokens per second — a comfortable fit.

Can I run Wuerstchen on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 1.8 GB and generating roughly 386 tokens per second — a comfortable fit.

Can I run Wuerstchen on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 1.8 GB and generating roughly 479 tokens per second — a comfortable fit.

Can I run Wuerstchen on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 1.8 GB and generating roughly 568 tokens per second — a comfortable fit.

Is Wuerstchen open source?

Its weights are published, so Wuerstchen 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 Wuerstchen have?

Wuerstchen has 1B parameters. 1B. 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 Wuerstchen?

Wuerstchen was published by Technische Hochschule Ingolstadt,University of Montreal / Université de Montréal,Mila - Quebec AI (originally Montreal Institute for Learning Algorithms),Polytechnique Montreal,Wand Technologies, based in Germany, categorised as academia,Academia,Academia,Academia,Industry.

When was Wuerstchen released?

Wuerstchen was published in September 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 Wuerstchen used for?

Wuerstchen works in Image generation, and is recorded as handling text-to-image, Image 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.

Where can I download Wuerstchen?

Its weights are published under the dome272 organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.

How much compute was used to train Wuerstchen?

Around 8.3 × 10²¹ 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.

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

It can be split between the card and system memory, but Wuerstchen generates painfully slowly that way. Nothing on this page assumes offloading.

Would two GPUs run Wuerstchen faster?

Two cards buy memory rather than speed. That matters for Wuerstchen only if one card cannot hold it — 818 can, so a second adds little.

Why does the quantisation differ between cards for Wuerstchen?

Because capacity varies, so does how hard Wuerstchen has to be squeezed — 1 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these Wuerstchen speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 2,033–5,421 tok/s on the B200, for instance. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

What GPU do I need to run Wuerstchen?

The smallest card in our catalogue that holds Wuerstchen is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 1.8 GB, and produces roughly 36.9 tokens per second. 818 cards in total can run it.

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