DALL-E mega

Open weights Craiyon June 2022

No estimate

No hardware requirements for this model

This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.

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
Craiyon
Organisation type
Industry
Country
United States of America
Published
28 June 2022
Authors
Dayma, Boris and Patil, Suraj and Cuenca, Pedro and Saifullah, Khalid and Abraham, Tanishq and Lê Khắc, Phúc and Melas, Luke and Ghosh, Ritobrata

What it does

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

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

possible the same data as DALL-E mini

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
2.3 × 10²² FLOP

flops = (128) * (1.23e14) * (1344 * 3600) * (0.3) = 2.3e22 (num gpu) * (peak flops) * (time in seconds) * (assumed utilization rate) from https://huggingface.co/dalle-mini/dalle-mega#environmental-impact

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
Google TPU v3
Chips used
128
Chip-hours
172,032
Wall-clock time
1,344 hours (56 days)

from https://huggingface.co/dalle-mini/dalle-mega#environmental-impact

Power draw
115.5 kW

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

apache 2.0 training journal: https://wandb.ai/dalle-mini/dalle-mini/reports/DALL-E-Mega-Training--VmlldzoxODMxMDI2#training-parameters

How it is classified

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

Record confidence
Confident

Sources

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

Reference
DALL·E Mega Model Card
Last updated
28 November 2025

What the numbers mean

About this model

DALL-E mega was published by Craiyon, in United States of America, in June 2022. It comes out of industry.

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

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.

Training and provenance

Producing it required around 2.3 × 10²² FLOP of arithmetic, on Google TPU v3, which is a statement about the training budget rather than about inference.

Answers

DALL-E mega — common questions

01

How many parameters does DALL-E mega have?

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

02

Who created DALL-E mega?

DALL-E mega was published by Craiyon, based in United States of America, categorised as industry.

03

When was DALL-E mega released?

DALL-E mega was published in June 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.

04

What is DALL-E mega used for?

DALL-E mega works in Image generation, and is recorded as handling text-to-image, Image generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

05

Where can I download DALL-E mega?

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

06

How much compute was used to train DALL-E mega?

Around 2.3 × 10²² FLOP, on Google TPU v3. 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.

07

What GPU do I need to run DALL-E mega?

We cannot say. DALL-E mega has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.

08

Is DALL-E mega open source?

Its weights are published, so DALL-E mega 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.

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.