LDM-1.45B TPS calculator

Open weights Heidelberg University,Runway 1.5B parameters December 2021

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 LDM-1.45B?

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: Heidelberg University,Runway
Organisation type: Academia,Industry
Country: Germany, United States of America
Published: 20 December 2021
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

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: 291,985,200,000 tokens
Epochs: 0.66

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

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

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: 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 LDM-1.45B

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 LDM-1.45B

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

2.3 GB

Fastest

2,337 tok/s

LDM-1.45B 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 smallest card that holds it is the Tesla C1080 with 4 GB, running it at Q8_0 and producing around 25.4 tokens per second.

The quickest result comes from a B200 at around 2,337 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

Background

LDM-1.45B was published by Heidelberg University,Runway, in Germany, in December 2021. The organisation is categorised as academia,Industry.

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

Published weights mean the model runs on your machine rather than someone else's, which is what makes the hardware question below answerable at all.

Reading the throughput figures

The median result is around 65.6 tokens per second; 796 cards produce text faster than most people read it.

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

It was trained on about 291,985,200,000 tokens of text.

The reason it appears in this catalogue at all is highly cited.

Step by step

How to choose a GPU for LDM-1.45B

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 LDM-1.45B actually needs — around 2.3 GB at Q8_0. No amount of processing power compensates for a card that cannot hold it.
02

Decide how long your conversations run

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context LDM-1.45B can slip off a card that handles short questions easily.
03

Set a quality floor

Each card runs the least-compressed copy it can hold — Q8_0 on the smallest card that fits. Setting a floor drops the cards that only manage LDM-1.45B by squeezing it further than you would want.
04

Sort by speed

The speed ordering for LDM-1.45B is effectively an ordering by memory bandwidth, which is why the B200 tops it at 2,337 tok/s.
05

Check the fit verdict before buying

A tight fit runs LDM-1.45B but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
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 LDM-1.45B is settled.

Answers

LDM-1.45B — common questions

How much VRAM does LDM-1.45B 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 LDM-1.45B 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 LDM-1.45B 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 LDM-1.45B 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 LDM-1.45B 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.

Is LDM-1.45B open source?

Its weights are published, so LDM-1.45B 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 LDM-1.45B have?

LDM-1.45B has 1.5B parameters. 1.45B. 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 LDM-1.45B?

LDM-1.45B was published by Heidelberg University,Runway, based in Germany, categorised as academia,Industry.

When was LDM-1.45B released?

LDM-1.45B was published in December 2021. 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 LDM-1.45B used for?

LDM-1.45B 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 LDM-1.45B?

The weights for LDM-1.45B are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

Can I run LDM-1.45B 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 LDM-1.45B is rarely worth using. Every figure here assumes the whole model is on the card.

Would two GPUs run LDM-1.45B faster?

A second card roughly doubles the memory available but not the generation rate. With 818 cards already able to run LDM-1.45B alone, the case for pairing is weak.

Why does the quantisation differ between cards for LDM-1.45B?

Because capacity varies, so does how hard LDM-1.45B has to be squeezed — 1 distinct levels appear in the table above. Set a minimum quality to compare at one.

How accurate are these LDM-1.45B speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 1,402–3,739 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 LDM-1.45B?

The smallest card in our catalogue that holds LDM-1.45B 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 LDM-1.45B 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 LDM-1.45B clear that.

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