Diamond
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
- University of Geneva,University of Edinburgh,Microsoft Research
- Organisation type
- Academia,Academia,Industry
- Country
- Switzerland, United Kingdom of Great Britain and Northern Ireland, United States of America
- Published
- 20 May 2024
- Authors
- Eloi Alonso, Adam Jelley, Vincent Micheli, Anssi Kanervisto, Amos Storkey, Tim Pearce, François Fleuret
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Games
- Task
- Atari
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
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
- 8 × 10²⁰ FLOP
- How it was established
- Hardware
82600000000000*9022.8*3600*0.3=8.0490594e+20
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 GeForce RTX 4090
- Wall-clock time
- 9,023 hours (376 days)
"We trained DIAMOND from scratch for 5 random seeds on each game. Each run utilized around 12GB of VRAM and took approximately 2.9 days on a single Nvidia RTX 4090 (1.03 GPU years in total)." 1.03*365*24 = 9022.8
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)
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Likely
Sources
Where this record came from and when it was last checked.
- Reference
- Diffusion for World Modeling: Visual Details Matter in Atari
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
Diamond was published by University of Geneva,University of Edinburgh,Microsoft Research, in the country recorded as Switzerland, during May 2024. It comes out of an organisation categorised as academia,Academia,Industry.
It works in the domain of Games, and is recorded as performing the task of atari.
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.
How it was trained
The training run consumed about 8 × 10²⁰ FLOP, on hardware recorded as NVIDIA GeForce RTX 4090. That figure measures what producing the model cost, and has no bearing on how fast it answers.
Answers
Diamond — common questions
Diamond— what GPU do I need to run it?
We cannot say. It 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.
Diamond— 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.
Diamond— how many parameters does it have?
No parameter count has been published for it, which is why no memory or speed figure appears on this page.
Diamond— who created it?
It was published by University of Geneva,University of Edinburgh,Microsoft Research, based in Switzerland, an organisation categorised as academia,Academia,Industry.
Diamond— when was it released?
It was published in May 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.
Diamond— what is it used for?
It works in the domain of Games, and is recorded as handling the task of atari. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
Diamond— where can I download it?
The weights are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
Diamond— how much compute was used to train it?
Training consumed around 8 × 10²⁰ FLOP, on hardware recorded as NVIDIA GeForce RTX 4090. 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.
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.