Stable Diffusion XL (SDXL) TPS calculator

Open weights Stability AI 3.4B parameters July 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 · 15.8 tok/s

Fastest card

B200

997 tok/s · 180 GB

Which GPUs can run Stable Diffusion XL (SDXL)?

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
997 tok/s 598–1,594 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	4.3 GB	Q8_0	Comfortable
997 tok/s 598–1,594 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	4.3 GB	Q8_0	Comfortable
796 tok/s 477–1,273 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	4.3 GB	Q8_0	Comfortable
796 tok/s 477–1,273 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	4.3 GB	Q8_0	Comfortable
636 tok/s 382–1,018 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	4.3 GB	Q8_0	Comfortable
609 tok/s 365–975 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	4.3 GB	Q8_0	Comfortable
609 tok/s 365–975 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	4.3 GB	Q8_0	Comfortable
583 tok/s 350–933 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	4.3 GB	Q8_0	Comfortable
517 tok/s 310–828 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	4.3 GB	Q8_0	Comfortable
517 tok/s 310–828 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	4.3 GB	Q8_0	Comfortable
517 tok/s 310–828 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	4.3 GB	Q8_0	Comfortable
491 tok/s 294–785 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	4.3 GB	Q8_0	Comfortable
419 tok/s 251–670 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	4.3 GB	Q8_0	Comfortable
419 tok/s 251–670 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	4.3 GB	Q8_0	Comfortable
419 tok/s 251–670 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	4.3 GB	Q8_0	Comfortable
419 tok/s 251–670 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	4.3 GB	Q8_0	Comfortable
419 tok/s 251–670 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	4.3 GB	Q8_0	Comfortable
319 tok/s 191–510 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	4.3 GB	Q8_0	Comfortable
319 tok/s 191–510 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	4.3 GB	Q8_0	Comfortable
266 tok/s 159–425 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	4.3 GB	Q8_0	Comfortable
260 tok/s 156–416 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	4.3 GB	Q8_0	Comfortable
254 tok/s 152–407 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	4.3 GB	Q8_0	Comfortable
254 tok/s 152–407 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	4.3 GB	Q8_0	Comfortable
254 tok/s 152–407 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	4.3 GB	Q8_0	Comfortable
254 tok/s 152–407 · 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: Stability AI
Organisation type: Industry
Country: United Kingdom of Great Britain and Northern Ireland
Published: 4 July 2023
Authors: Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas Müller, Joe Penna, Robin Rombach

What it does

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

Domain: Image generation
Task: Image generation, Text-to-image

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: 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: stabilityai

How it is classified

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

Likely above 10²³ FLOP: Yes
Why it is tracked: Significant use
Record confidence: Speculative
Citations: 4,666

Sources

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

Reference: SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run Stable Diffusion XL (SDXL)

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 Stable Diffusion XL (SDXL)

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

997 tok/s

Stable Diffusion XL (SDXL) 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 15.8 tokens per second.

A B200 is the fastest we calculate for it: about 997 tokens per second, from 8,000 GB/s of memory bandwidth.

About this model

Stable Diffusion XL (SDXL) was published by Stability AI, in United Kingdom of Great Britain and Northern Ireland, in July 2023. The organisation is categorised as industry.

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

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 stabilityai organisation on Hugging Face.

How fast it runs, and why

The median result is around 31.6 tokens per second; 777 cards produce text faster than most people read it.

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.

How it was trained

Its inclusion criterion is significant use.

Step by step

How to choose a GPU for Stable Diffusion XL (SDXL)

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

The table lists every card that can hold Stable Diffusion XL (SDXL) — around 3.5 GB at Q6_K. That figure, not the card's headline performance, is what decides whether it runs.
02

Set the context length you will work at

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for Stable Diffusion XL (SDXL).
03

Set a quality floor

Compression is what makes Stable Diffusion XL (SDXL) fit smaller cards, at some cost in accuracy — Q6_K 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 Stable Diffusion XL (SDXL) is effectively an ordering by memory bandwidth, which is why the B200 tops it at 997 tok/s.
05

Check the fit verdict before buying

The fit column separates cards that just manage Stable Diffusion XL (SDXL) from those with room to spare. Buy for the second if the context might grow.
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 Stable Diffusion XL (SDXL) is settled.

Answers

Stable Diffusion XL (SDXL) — common questions

Is Stable Diffusion XL (SDXL) open source?

Its weights are published, so Stable Diffusion XL (SDXL) 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 Stable Diffusion XL (SDXL) have?

Stable Diffusion XL (SDXL) has 3.4B parameters. "...result in a model size of 2.6B parameters in the UNet, see Tab. 1. The text encoders have a total size of 817M parameters.". 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 Stable Diffusion XL (SDXL)?

Stable Diffusion XL (SDXL) was published by Stability AI, based in United Kingdom of Great Britain and Northern Ireland, categorised as industry.

When was Stable Diffusion XL (SDXL) released?

Stable Diffusion XL (SDXL) was published in July 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 Stable Diffusion XL (SDXL) used for?

Stable Diffusion XL (SDXL) works in Image generation, and is recorded as handling image generation, Text-to-image. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download Stable Diffusion XL (SDXL)?

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

Can I run Stable Diffusion XL (SDXL) 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 Stable Diffusion XL (SDXL) is rarely worth using. Every figure here assumes the whole model is on the card.

Would two GPUs run Stable Diffusion XL (SDXL) faster?

Capacity adds across cards; throughput does not. Since 818 of the cards we track already hold Stable Diffusion XL (SDXL) on their own, a second card is rarely the answer here.

Why does the quantisation differ between cards for Stable Diffusion XL (SDXL)?

Each card is shown running the least-compressed copy it can hold, and Stable Diffusion XL (SDXL) appears at 2 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these Stable Diffusion XL (SDXL) speed estimates?

These are estimates with real error bars. The fastest result here, 598–1,594 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

What GPU do I need to run Stable Diffusion XL (SDXL)?

The smallest card in our catalogue that holds Stable Diffusion XL (SDXL) is the Tesla C1080, with 4 GB of memory. It runs the model at Q6_K using about 3.5 GB, and produces roughly 15.8 tokens per second. 818 cards in total can run it.

How fast is Stable Diffusion XL (SDXL) on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 997 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 777 of the cards that can run Stable Diffusion XL (SDXL) clear that.

How much VRAM does Stable Diffusion XL (SDXL) 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 Stable Diffusion XL (SDXL) 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 186 tokens per second — a comfortable fit.

Can I run Stable Diffusion XL (SDXL) 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 114 tokens per second — a comfortable fit.

Can I run Stable Diffusion XL (SDXL) 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 141 tokens per second — a comfortable fit.

Can I run Stable Diffusion XL (SDXL) 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 167 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