AlphaGenome
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
- Google DeepMind
- Organisation type
- Industry
- Country
- United States of America
- Published
- 25 June 2025
- Authors
- Žiga Avsec, Natasha Latysheva, Jun Cheng, Guido Novati, Kyle R. Taylor, Tom Ward, Clare Bycroft, Lauren Nicolaisen, Eirini Arvaniti, Joshua Pan, Raina Thomas, Vincent Dutordoir, Matteo Perino, Soham De, Alexander Karollus, Adam Gayoso, Toby Sargeant, Anne Mottram, Lai Hong Wong, Pavol Drotár, Adam Kosiorek, Andrew Senior, Richard Tanburn, Taylor Applebaum, Souradeep Basu, Demis Hassabis, Pushmeet …
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- Gene expression enhancement, Gene expression profile generation, Molecular property prediction, Mutation prediction, Protein-DNA binding prediction, Transcriptomic prediction, RNA structure prediction
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
- 450M
- Training data
- tokens
" AlphaGenome has approximately 450 million trainable parameters (20% in the encoder, 28% in the sequence transformer, 15% in the pairwise blocks, 25% in the decoder, and 12% in the output embedding and prediction heads)"
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
- 1.4 × 10²² FLOP
- How it was established
- Hardware
Pre-training: "Each gradient step processed a batch size of 64 samples using 8-way sequence parallelism, requiring 512 TPUv3 cores, with pre-training runs typically completing in approximately 4 hours." "Distillation using many teacher models (e.g., 64; orange crosses)" 123000000000000 FLOP / TPUv3 chip / sec * (512 TPUv3 cores / 2) * 4 hours * 3600 sec / hour * 0.3 [assumed utilization] * 64 training runs ["Likely" confidence] = 8.7058022e+21 FLOP Distillation: "Distillation training was per…
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,NVIDIA H100 SXM5 80GB
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
- Closed — provider access only
- Model access
- API access
- Training code
- Unreleased
"To advance scientific research, we’re making AlphaGenome available in preview via our AlphaGenome API for non-commercial research, and planning to release the model in the future."
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
- AlphaGenome: advancing regulatory variant effect prediction with a unified DNA sequence model
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
AlphaGenome was published by Google DeepMind, in United States of America, in June 2025. The organisation is categorised as industry.
It works in Biology, and is recorded as doing gene expression enhancement, Gene expression profile generation, Molecular property prediction, Mutation prediction, Protein-DNA binding prediction, Transcriptomic prediction, RNA structure prediction.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Training and provenance
The training run consumed about 1.4 × 10²² FLOP, on Google TPU v3,NVIDIA H100 SXM5 80GB. That figure describes the cost of creating it and has no bearing on how quickly it generates text.
Answers
AlphaGenome — common questions
Is AlphaGenome open source?
No. AlphaGenome has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does AlphaGenome have?
AlphaGenome has 450M parameters. " AlphaGenome has approximately 450 million trainable parameters (20% in the encoder, 28% in the sequence transformer, 15% in the pairwise blocks, 25% in the decoder, and 12% in the output embedding and prediction heads)". 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 AlphaGenome?
AlphaGenome was published by Google DeepMind, based in United States of America, categorised as industry.
When was AlphaGenome released?
AlphaGenome was published in June 2025.
What is AlphaGenome used for?
AlphaGenome works in Biology, and is recorded as handling gene expression enhancement, Gene expression profile generation, Molecular property prediction, Mutation prediction, Protein-DNA binding prediction, Transcriptomic prediction, RNA structure prediction. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
How much compute was used to train AlphaGenome?
Around 1.4 × 10²² FLOP, on Google TPU v3,NVIDIA H100 SXM5 80GB. 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 AlphaGenome?
None. AlphaGenome 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.
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.