ESMFlow
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
- Massachusetts Institute of Technology (MIT)
- Organisation type
- Academia
- Country
- United States of America
- Published
- 2 September 2024
- Authors
- Bowen Jing, Bonnie Berger, Tommi Jaakkola
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- Protein folding 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.
- Training data
- 552,960,000 tokens
ESMFLOW: 720K × 256 = 184,320,000 27K × 256 = 6,912,000 Total: 184,320,000 + 6,912,000 = 191,232,000
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
- 7.6 × 10²⁰ FLOP
- How it was established
- Reported
1. Hardware setup: 8x NVIDIA A100 GPUs, 3.12e+14 FLOP/s per GPU 2. Training duration: 371 hours (267h AlphaFLOW + 104h ESMFLOW) = 1,335,600 seconds 3. Utilization rate: 40% 4. Final calculation: 8 GPUs × 3.12e+14 FLOP/s × 1,335,600s × 0.4 = 1.34e+21 FLOPs ESMFlow training time, table 2 104+37+5+34+9+23=212 212hours*8*3.12e14*0.4=761978880000000000000
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
- 8
- Power draw
- 6.3 kW
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)
- Training code
- Open source
MIT license https://github.com/bjing2016/alphaflow
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
- 237
Sources
Where this record came from and when it was last checked.
- Reference
- AlphaFold Meets Flow Matching for Generating Protein Ensembles
- Last updated
- 25 May 2026
What the numbers mean
Where it came from
ESMFlow was published by Massachusetts Institute of Technology (MIT), in United States of America, in September 2024. academia is the category the publisher falls under.
It works in Biology, and is recorded as doing protein folding prediction.
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.
What went into building it
Producing it required around 7.6 × 10²⁰ FLOP of arithmetic, on NVIDIA A100, which is a statement about the training budget rather than about inference.
It was trained on about 552,960,000 tokens of text.
Answers
ESMFlow — common questions
What is ESMFlow used for?
ESMFlow works in Biology, and is recorded as handling protein folding prediction. 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.
Where can I download ESMFlow?
The weights for ESMFlow are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
How much compute was used to train ESMFlow?
Around 7.6 × 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 ESMFlow?
We cannot say. ESMFlow 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.
Is ESMFlow open source?
Its weights are published, so ESMFlow 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.
How many parameters does ESMFlow have?
No parameter count has been published for ESMFlow, which is why no memory or speed figure appears on this page.
Who created ESMFlow?
ESMFlow was published by Massachusetts Institute of Technology (MIT), based in United States of America, categorised as academia.
When was ESMFlow released?
ESMFlow was published in September 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.
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.