OMNI-EPIC
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
- Imperial College London,University of British Columbia (UBC)
- Organisation type
- Academia,Academia
- Country
- United Kingdom of Great Britain and Northern Ireland, Canada
- Published
- 24 May 2024
- Authors
- Maxence Faldor, Jenny Zhang, Antoine Cully, Jeff Clune
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Code 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
RL, so the natural unit is environment steps, see "Table 2: DreamerV3 hyperparameters"
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 × 10¹⁷ FLOP
3600 * 2 * (91.1 * 10^12) * 0.35 = 2.3e17
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
- 57
Sources
Where this record came from and when it was last checked.
- Reference
- OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code
- Last updated
- 25 May 2026
What the numbers mean
Where it came from
OMNI-EPIC was published by Imperial College London,University of British Columbia (UBC), in United Kingdom of Great Britain and Northern Ireland, in May 2024. academia,Academia is the category the publisher falls under.
It works in Language, and is recorded as doing code generation.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
What went into building it
The training run consumed about 2.3 × 10¹⁷ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.
Answers
OMNI-EPIC — common questions
Who created OMNI-EPIC?
OMNI-EPIC was published by Imperial College London,University of British Columbia (UBC), based in United Kingdom of Great Britain and Northern Ireland, categorised as academia,Academia.
When was OMNI-EPIC released?
OMNI-EPIC 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.
What is OMNI-EPIC used for?
OMNI-EPIC works in Language, and is recorded as handling code generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
How much compute was used to train OMNI-EPIC?
Around 2.3 × 10¹⁷ FLOP. 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.
What GPU do I need to run OMNI-EPIC?
None. OMNI-EPIC 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.
Is OMNI-EPIC open source?
The licensing for OMNI-EPIC was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
How many parameters does OMNI-EPIC have?
No parameter count has been published for OMNI-EPIC, which is why no memory or speed figure appears on this page.
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.