Stable Diffusion (LDM-KL-8-G) TPS calculator

Open weights Runway,Ludwig Maximilian University of Munich,Heidelberg University 1.5B parameters April 2022

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 · 25.4 tok/s

Fastest card

B200

2,337 tok/s · 180 GB

Which GPUs can run Stable Diffusion (LDM-KL-8-G)?

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
2,337 tok/s 1,402–3,739 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	2.3 GB	Q8_0	Comfortable
2,337 tok/s 1,402–3,739 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	2.3 GB	Q8_0	Comfortable
1,866 tok/s 1,120–2,985 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	2.3 GB	Q8_0	Comfortable
1,866 tok/s 1,120–2,985 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	2.3 GB	Q8_0	Comfortable
1,492 tok/s 895–2,388 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	2.3 GB	Q8_0	Comfortable
1,428 tok/s 857–2,285 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	2.3 GB	Q8_0	Comfortable
1,428 tok/s 857–2,285 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	2.3 GB	Q8_0	Comfortable
1,367 tok/s 820–2,187 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	2.3 GB	Q8_0	Comfortable
1,213 tok/s 728–1,941 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	2.3 GB	Q8_0	Comfortable
1,213 tok/s 728–1,941 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	2.3 GB	Q8_0	Comfortable
1,213 tok/s 728–1,941 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	2.3 GB	Q8_0	Comfortable
1,151 tok/s 691–1,841 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	2.3 GB	Q8_0	Comfortable
981 tok/s 589–1,570 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	2.3 GB	Q8_0	Comfortable
981 tok/s 589–1,570 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	2.3 GB	Q8_0	Comfortable
981 tok/s 589–1,570 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	2.3 GB	Q8_0	Comfortable
981 tok/s 589–1,570 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	2.3 GB	Q8_0	Comfortable
981 tok/s 589–1,570 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	2.3 GB	Q8_0	Comfortable
747 tok/s 448–1,196 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	2.3 GB	Q8_0	Comfortable
747 tok/s 448–1,196 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	2.3 GB	Q8_0	Comfortable
623 tok/s 374–996 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	2.3 GB	Q8_0	Comfortable
609 tok/s 366–975 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	2.3 GB	Q8_0	Comfortable
596 tok/s 358–953 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	2.3 GB	Q8_0	Comfortable
596 tok/s 358–953 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	2.3 GB	Q8_0	Comfortable
596 tok/s 358–953 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	2.3 GB	Q8_0	Comfortable
596 tok/s 358–953 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	2.3 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: Runway,Ludwig Maximilian University of Munich,Heidelberg University
Organisation type: Industry,Academia,Academia
Country: United States of America, Germany
Published: 13 April 2022
Authors: Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, Björn Ommer

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
Approach: Self-supervised learning
Base model: Stable Diffusion 1.2

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: 1.5B
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: 5 × 10²² FLOP
How it was established: Hardware

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware: NVIDIA A100
Chips used: 256
Chip-hours: 150,000
Wall-clock time: 586 hours (24.4 days)
Power draw: 205.8 kW
Compute cost: $111,248

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)
Training code: Open source
Hugging Face: CompVis

How it is classified

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

Why it is tracked: Significant use,Highly cited
Record confidence: Confident
Citations: 24,523

Sources

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

Reference: High-Resolution Image Synthesis with Latent Diffusion Models
Last updated: 25 May 2026

The extremes

The ten fastest GPUs that run Stable Diffusion (LDM-KL-8-G)

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 (LDM-KL-8-G)

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

2.3 GB

Fastest

2,337 tok/s

Stable Diffusion (LDM-KL-8-G) is small enough at 1.5B 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 25.4 tokens per second.

A B200 is the fastest we calculate for it: about 2,337 tokens per second, from 8,000 GB/s of memory bandwidth.

Background

Stable Diffusion (LDM-KL-8-G) was published by Runway,Ludwig Maximilian University of Munich,Heidelberg University, in United States of America, in April 2022. The organisation is categorised as industry,Academia,Academia.

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

It builds on Stable Diffusion 1.2, which is why it shares that model's general shape and size.

The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold. It is published under the CompVis organisation on Hugging Face.

Reading the throughput figures

Across every card that can run it, the middle of the range is about 65.6 tokens per second, and 796 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.

Memory here is estimated from size rather than computed from the architecture, which is not recorded for this model — the numbers are indicative rather than exact.

What went into building it

Producing it required around 5 × 10²² FLOP of arithmetic, on NVIDIA A100, which is a statement about the training budget rather than about inference.

It is tracked in the underlying dataset for one reason in particular: significant use,Highly cited.

Step by step

How to choose a GPU for Stable Diffusion (LDM-KL-8-G)

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

01

Check what it needs before anything else

Every card here has been checked against Stable Diffusion (LDM-KL-8-G) — around 2.3 GB at Q8_0. 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 (LDM-KL-8-G).
03

Choose how far you will compress it

The quantisation column varies by card, because a bigger card holds a more accurate copy of Stable Diffusion (LDM-KL-8-G) — Q8_0 on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Rank by throughput rather than spec sheet

Ranking by tokens per second for Stable Diffusion (LDM-KL-8-G) follows memory bandwidth, not core counts, which is why the B200 tops it at 2,337 tok/s.
05

Look at the headroom, not just the fit

The fit column separates cards that just manage Stable Diffusion (LDM-KL-8-G) from those with room to spare. Buy for the second if the context might grow.
06

Open the card you have settled on

Following a card through to its own page shows every other model it can hold, which is the question that follows once Stable Diffusion (LDM-KL-8-G) is settled.

Answers

Stable Diffusion (LDM-KL-8-G) — common questions

Is Stable Diffusion (LDM-KL-8-G) open source?

Its weights are published, so Stable Diffusion (LDM-KL-8-G) 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 (LDM-KL-8-G) have?

Stable Diffusion (LDM-KL-8-G) has 1.5B parameters. See Table 2. 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 (LDM-KL-8-G)?

Stable Diffusion (LDM-KL-8-G) was published by Runway,Ludwig Maximilian University of Munich,Heidelberg University, based in United States of America, categorised as industry,Academia,Academia.

When was Stable Diffusion (LDM-KL-8-G) released?

Stable Diffusion (LDM-KL-8-G) was published in April 2022. 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 (LDM-KL-8-G) used for?

Stable Diffusion (LDM-KL-8-G) works in Image generation, and is recorded as handling image generation, Text-to-image. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download Stable Diffusion (LDM-KL-8-G)?

Its weights are published under the CompVis 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 Stable Diffusion (LDM-KL-8-G)?

Around 5 × 10²² FLOP, on NVIDIA A100. 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 Stable Diffusion (LDM-KL-8-G) if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part in system memory drags the whole thing down. Our figures for Stable Diffusion (LDM-KL-8-G) assume it is fully resident.

Would two GPUs run Stable Diffusion (LDM-KL-8-G) faster?

Two cards buy memory rather than speed. That matters for Stable Diffusion (LDM-KL-8-G) only if one card cannot hold it — 818 can, so a second adds little.

Why does the quantisation differ between cards for Stable Diffusion (LDM-KL-8-G)?

A larger card holds a more accurate copy. Across the cards that run Stable Diffusion (LDM-KL-8-G), 1 compression levels are used; the floor control above pins it to one.

How accurate are these Stable Diffusion (LDM-KL-8-G) speed estimates?

These are estimates with real error bars. The fastest result here, 1,402–3,739 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 (LDM-KL-8-G)?

The smallest card in our catalogue that holds Stable Diffusion (LDM-KL-8-G) is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 2.3 GB, and produces roughly 25.4 tokens per second. 818 cards in total can run it.

How fast is Stable Diffusion (LDM-KL-8-G) on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 2,337 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 796 of the cards that can run Stable Diffusion (LDM-KL-8-G) clear that.

How much VRAM does Stable Diffusion (LDM-KL-8-G) need?

About 2.3 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 Stable Diffusion (LDM-KL-8-G) on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 2.3 GB and generating roughly 435 tokens per second — a comfortable fit.

Can I run Stable Diffusion (LDM-KL-8-G) on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 2.3 GB and generating roughly 267 tokens per second — a comfortable fit.

Can I run Stable Diffusion (LDM-KL-8-G) on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 2.3 GB and generating roughly 330 tokens per second — a comfortable fit.

Can I run Stable Diffusion (LDM-KL-8-G) on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 2.3 GB and generating roughly 391 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