PoET
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
- OpenProtein.ai
- Organisation type
- Industry
- Country
- Singapore
- Published
- 9 June 2023
- Authors
- Timothy F. Truong Jr, Tristan Bepler
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- Protein generation, 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
- 57M
- Training data
- tokens
29,000,000 sets * 10 sequences/set = 290,000,000 sequences Tokens per sequence = 300 amino acids + 2 tokens = 302 tokens Total tokens = 290,000,000 sequences * 302 tokens/sequence = 87,580,000,000 Final result: 8.758 × 10¹⁰ datapoints
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 × 10²⁰ FLOP
- How it was established
- Hardware
1. Hardware setup: 7x NVIDIA A100 GPUs, 3.12e14 FLOP/s per GPU 2. Training duration: 3 days = 259,200 seconds (directly provided) 3. Utilization rate: 40% (default assumption) 4. Calculation: 3.12e14 FLOP/s × 7 GPUs × 259,200s × 0.4 = 2.3e20 FLOPs
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 A100
- Chips used
- 7
- Wall-clock time
- 72 hours
- Power draw
- 5.6 kW
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
- 83
Sources
Where this record came from and when it was last checked.
- Reference
- PoET: A generative model of protein families as sequences-of-sequences
- Last updated
- 25 May 2026
What the numbers mean
About this model
PoET was published by OpenProtein.ai, in Singapore, in June 2023. It comes out of industry.
It works in Biology, and is recorded as doing protein generation, Protein or nucleotide language model (pLM/nLM).
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
What went into building it
Training it took roughly 2.3 × 10²⁰ FLOP of computation, on NVIDIA A100 — a measure of what producing the model cost, not of how fast it answers.
Answers
PoET — common questions
Who created PoET?
PoET was published by OpenProtein.ai, based in Singapore, categorised as industry.
When was PoET released?
PoET was published in June 2023. 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 PoET used for?
PoET works in Biology, and is recorded as handling protein generation, Protein or nucleotide language model (pLM/nLM). Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
How much compute was used to train PoET?
Around 2.3 × 10²⁰ FLOP, on NVIDIA A100. 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 PoET?
None. PoET 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 PoET open source?
The licensing for PoET 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 PoET have?
PoET has 57M 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.
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.