CHAI-1
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
- Chai discovery
- Organisation type
- Industry
- Country
- United States of America
- Published
- 15 October 2024
- Authors
- Jacques Boitreaud, Jack Dent, Matthew McPartlon, Joshua Meier, Vinicius Reis, Alex Rogozhnikov, Kevin Wu
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- Protein folding prediction, Protein-ligand contact prediction
- Numerical format
- BF16
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
- Batch size
- 128
Taken from paper
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
- 7.8 × 10²¹ FLOP
- How it was established
- Hardware
From paper: 128 A100s for 30 days; assumptions: 30% utilization rate, FP16 precision
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
- 128
- Wall-clock time
- 720 hours (30 days)
- Power draw
- 100.8 kW
Taken from paper: 128 A100s for 30 days
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 (non-commercial)
- Training code
- Open (non-commercial)
https://github.com/chaidiscovery/chai-lab?tab=License-1-ov-file
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Why it is tracked
- SOTA improvement
- Record confidence
- Confident
Matches or beats AF3 on Ligand PoseBusters
Sources
Where this record came from and when it was last checked.
- Reference
- Introducing Chai-1: Decoding the molecular interactions of life
- Last updated
- 28 November 2025
What the numbers mean
About this model
CHAI-1 was published by Chai discovery, in United States of America, in October 2024. It comes out of industry.
It works in Biology, and is recorded as doing protein folding prediction, Protein-ligand contact prediction.
The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold.
How it was trained
Producing it required around 7.8 × 10²¹ FLOP of arithmetic, on NVIDIA A100, which is a statement about the training budget rather than about inference.
The reason it appears in this catalogue at all is sOTA improvement.
Answers
CHAI-1 — common questions
Who created CHAI-1?
CHAI-1 was published by Chai discovery, based in United States of America, categorised as industry.
When was CHAI-1 released?
CHAI-1 was published in October 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 CHAI-1 used for?
CHAI-1 works in Biology, and is recorded as handling protein folding prediction, Protein-ligand contact prediction. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
Where can I download CHAI-1?
The weights for CHAI-1 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 CHAI-1?
Around 7.8 × 10²¹ 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 CHAI-1?
We cannot say. CHAI-1 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 CHAI-1 open source?
Its weights are published, so CHAI-1 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 CHAI-1 have?
No parameter count has been published for CHAI-1, 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.