Boltz-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
- Massachusetts Institute of Technology (MIT), Genesis Therapeutics
- Organisation type
- Academia,Industry
- Country
- United States of America
- Published
- 19 November 2024
- Authors
- Jeremy Wohlwend, Gabriele Corso, Saro Passaro, Mateo Reveiz, Ken Leidal, Wojtek Swiderski, Tally Portnoi, Itamar Chinn, Jacob Silterra, Tommi Jaakkola, Regina Barzilay
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, Protein interaction prediction, Protein structure comparison
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
"We train the structure prediction model <..> for a total of 68k steps with a batch size of 128. During the first 53k iterations, we use a crop size of 384 tokens and 3456 atoms <..>. For the last 15k iterations, we only sampled from the PDB structures and had a crop size of 512 tokens and 4608 atoms. " 53000*384*128+15000*512*128 = 3 588 096 000 tokens
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/jwohlwend/boltz
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
- Boltz-1: Democratizing Biomolecular Interaction Modeling
- Last updated
- 28 November 2025
What the numbers mean
About this model
Boltz-1 was published by Massachusetts Institute of Technology (MIT), Genesis Therapeutics, in United States of America, in November 2024. It comes out of academia,Industry.
It works in Biology, and is recorded as doing protein folding prediction, Protein-ligand contact prediction, Protein interaction prediction, Protein structure comparison.
Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.
Answers
Boltz-1 — common questions
Who created Boltz-1?
Boltz-1 was published by Massachusetts Institute of Technology (MIT), Genesis Therapeutics, based in United States of America, categorised as academia,Industry.
When was Boltz-1 released?
Boltz-1 was published in November 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 Boltz-1 used for?
Boltz-1 works in Biology, and is recorded as handling protein folding prediction, Protein-ligand contact prediction, Protein interaction prediction, Protein structure comparison. These are the areas it was designed around; they describe intent rather than a hard boundary.
Where can I download Boltz-1?
The weights for Boltz-1 are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
What GPU do I need to run Boltz-1?
We cannot say. Boltz-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 Boltz-1 open source?
Its weights are published, so Boltz-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 Boltz-1 have?
No parameter count has been published for Boltz-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.