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) reaches a parameter count of 3.4B. 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 entry point is Tesla C1080, with a memory capacity of 4 GB, running it at a compression of Q6_K and producing around 15.8 tokens per second.

The fastest we calculate for it is B200, generating roughly 997 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

About this model

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

It works in the domain of Image generation, and is recorded as performing the task of 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. On Hugging Face it is published under the organisation stabilityai.

How fast it runs, and why

The median result is around 31.6 tokens per second. Producing text faster than most people read it: 777 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.

How it was trained

Its inclusion criterion: 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 able to hold Stable Diffusion XL (SDXL), needing around 3.5 GB at a compression of Q6_K. Capacity is the gate — a card either holds it or it does not.
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 a model fit smaller cards, at some cost in accuracy, reaching a compression of Q6_K 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

Rank by throughput rather than spec sheet

The speed ordering is effectively an ordering by memory bandwidth, for Stable Diffusion XL (SDXL). It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 997 tok/s.
05

Check the fit verdict before buying

The fit column separates cards that just manage it from those with room to spare, in the case of Stable Diffusion XL (SDXL). 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 Stable Diffusion XL (SDXL).

Answers

Stable Diffusion XL (SDXL) — common questions

Stable Diffusion XL (SDXL)— 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.

Stable Diffusion XL (SDXL)— how many parameters does it have?

It has a parameter count of 3.4B. "...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.

Stable Diffusion XL (SDXL)— who created it?

It was published by Stability AI, based in United Kingdom of Great Britain and Northern Ireland, an organisation categorised as industry.

Stable Diffusion XL (SDXL)— when was it released?

It 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.

Stable Diffusion XL (SDXL)— what is it used for?

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

Stable Diffusion XL (SDXL)— where can I download it?

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

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

Stable Diffusion XL (SDXL)— would two GPUs run it faster?

Capacity adds across cards; throughput does not. The number of cards already holding it on their own: 818. So a second card is rarely the answer here.

Stable Diffusion XL (SDXL)— 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: 2. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Stable Diffusion XL (SDXL)— 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: 598–1,594 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Stable Diffusion XL (SDXL)— 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 Q6_K using about 3.5 GB, and produces roughly 15.8 tokens per second. The number of cards able to run it in total: 818.

Stable Diffusion XL (SDXL)— how fast is it on a GPU?

It depends on the card. The quickest we calculate is 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 the number of cards clearing that: 777.

Stable Diffusion XL (SDXL)— how much VRAM does it need?

It needs about 3.5 GB at a compression of Q6_K, 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.

Stable Diffusion XL (SDXL)— 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 4.3 GB and generating roughly 186 tokens per second. The fit is comfortable.

Stable Diffusion XL (SDXL)— 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 4.3 GB and generating roughly 114 tokens per second. The fit is comfortable.

Stable Diffusion XL (SDXL)— 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 4.3 GB and generating roughly 141 tokens per second. The fit is comfortable.

Stable Diffusion XL (SDXL)— 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 4.3 GB and generating roughly 167 tokens per second. The fit is comfortable.

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