OmniGenome
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 of Exeter
- Organisation type
- Academia
- Country
- United Kingdom of Great Britain and Northern Ireland
- Published
- 15 July 2024
- Authors
- Heng Yang, Ke Li
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- Protein or nucleotide language model (pLM/nLM)
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
- 186M
- Training data
- tokens
54.2 billion tokens = 54.2 x 10^9 = 54,200,000,000 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
- 3.4 × 10²⁰ FLOP
- How it was established
- Hardware
1. Hardware setup: 8x NVIDIA RTX 4090 GPUs (3.30×10¹⁴ FLOP/s per GPU) 2. Training duration: 3 weeks (directly provided) = 1,814,400 seconds (3 weeks × 7 days × 24 hours × 3600 seconds) 3. Utilization rate: 40% 4. Final calculation: 3.30×10¹⁴ FLOP/s × 8 GPUs × 1,814,400 seconds × 0.4 = 1.9×10²¹ FLOPs Alternative: 6*54.2B*186M=60487200000000000000 Geometric Mean: 339006902584593356472
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
- Chips used
- 8
- Power draw
- 7.1 kW
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Likely
- Citations
- 5
Sources
Where this record came from and when it was last checked.
- Reference
- OmniGenome: Aligning RNA Sequences with Secondary Structures in Genomic Foundation Models
- Last updated
- 25 May 2026
What the numbers mean
Background
OmniGenome was published by University of Exeter, in United Kingdom of Great Britain and Northern Ireland, in July 2024. It comes out of academia.
It works in Biology, and is recorded as doing protein or nucleotide language model (pLM/nLM).
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
What went into building it
The training run consumed about 3.4 × 10²⁰ FLOP, on NVIDIA GeForce RTX 4090. That figure describes the cost of creating it and has no bearing on how quickly it generates text.
Answers
OmniGenome — common questions
When was OmniGenome released?
OmniGenome was published in July 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 OmniGenome used for?
OmniGenome works in Biology, and is recorded as handling protein or nucleotide language model (pLM/nLM). 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.
How much compute was used to train OmniGenome?
Around 3.4 × 10²⁰ FLOP, on 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.
What GPU do I need to run OmniGenome?
None. OmniGenome 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 OmniGenome open source?
The licensing for OmniGenome 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 OmniGenome have?
OmniGenome has 186M parameters. 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 OmniGenome?
OmniGenome was published by University of Exeter, based in United Kingdom of Great Britain and Northern Ireland, categorised as academia.
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.