DDPM

Closed weights University Paris-Saclay,Radboud University Medical Center April 2024

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

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
University Paris-Saclay,Radboud University Medical Center
Organisation type
Academia,Academia
Country
France, Netherlands
Published
13 April 2024
Authors
Alice Lacan, Romain André, Michele Sebag, Blaise Hanczar

What it does

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

Domain
Biology
Task
Gene expression profile 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.

Training data
9,541,304 tokens

TCGA: 6,499 × 978 = 6,356,022 GTEx: 9,796 × 974 = 9,541,304 Total: 6,356,022 + 9,541,304 = 15,897,326 ≈ 1.6e7 datapoints

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
9 × 10¹⁷ FLOP

1. Hardware setup: 1x NVIDIA A40 GPU (1.50×10¹⁴ FLOP/s per GPU) 2. Training duration: 15,000 seconds (directly provided - sum of TCGA training: 3,780s and GTEx training: 11,220s) 3. Utilization rate: 40% 4. Calculation: 1.50×10¹⁴ FLOP/s × 1 GPU × 15,000s × 0.4 = 9.0×10¹⁷ FLOPs

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 A40 PCIe
Chips used
1
Power draw
326 W

How it is classified

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

Record confidence
Confident
Citations
4

Sources

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

Reference
In Silico Generation of Gene Expression profiles using Diffusion Models
Last updated
28 November 2025

What the numbers mean

Where it came from

DDPM was published by University Paris-Saclay,Radboud University Medical Center, in France, in April 2024. It comes out of academia,Academia.

It works in Biology, and is recorded as doing gene expression profile generation.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

How it was trained

Producing it required around 9 × 10¹⁷ FLOP of arithmetic, on NVIDIA A40 PCIe, which is a statement about the training budget rather than about inference.

Around 9,541,304 tokens went into training it.

Answers

DDPM — common questions

01

How many parameters does DDPM have?

No parameter count has been published for DDPM, which is why no memory or speed figure appears on this page.

02

Who created DDPM?

DDPM was published by University Paris-Saclay,Radboud University Medical Center, based in France, categorised as academia,Academia.

03

When was DDPM released?

DDPM was published in April 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

04

What is DDPM used for?

DDPM works in Biology, and is recorded as handling gene expression profile 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.

05

How much compute was used to train DDPM?

Around 9 × 10¹⁷ FLOP, on NVIDIA A40 PCIe. 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.

06

What GPU do I need to run DDPM?

None. DDPM is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

07

Is DDPM open source?

The licensing for DDPM was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

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.