FlexSBDD
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
- University of Science and Technology of China (USTC),State Key Laboratory of Cognitive Intelligence,Princeton University
- Organisation type
- Academia,Academia
- Country
- China, United States of America
- Published
- 29 September 2024
- Authors
- Zaixi Zhang, Mengdi Wang, Qi Liu
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- Drug discovery
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
- 3,675,000,000 tokens
Original pairs: 40,000 + 100,000 = 140,000 Estimated length ~300 tokens: 140000*300=42000000
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
- 1.6 × 10¹⁹ FLOP
- How it was established
- Hardware
1. Hardware: 1x NVIDIA A100 PCIe GPU (3.12e14 FP16 Tensor FLOP/s) 2. Training duration: 36 hours (directly provided) = 129,600 seconds 3. Utilization: 40% (assumed) 4. Calculation: 3.12e14 FLOP/s × 1 GPU × 129,600s × 0.4 = 1.6e19 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
- 1
- Wall-clock time
- 36 hours
- Power draw
- 433 W
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- FlexSBDD: Structure-Based Drug Design with Flexible Protein Modeling
- Last updated
- 28 November 2025
What the numbers mean
What this model is
FlexSBDD was published by University of Science and Technology of China (USTC),State Key Laboratory of Cognitive Intelligence,Princeton University, in China, in September 2024. The organisation is categorised as academia,Academia.
It works in Biology, and is recorded as doing drug discovery.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
How it was trained
Training it took roughly 1.6 × 10¹⁹ FLOP of computation, on NVIDIA A100 — a measure of what producing the model cost, not of how fast it answers.
It was trained on about 3,675,000,000 tokens of text.
Answers
FlexSBDD — common questions
What GPU do I need to run FlexSBDD?
None. FlexSBDD 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 FlexSBDD open source?
The licensing for FlexSBDD 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 FlexSBDD have?
No parameter count has been published for FlexSBDD, which is why no memory or speed figure appears on this page.
Who created FlexSBDD?
FlexSBDD was published by University of Science and Technology of China (USTC),State Key Laboratory of Cognitive Intelligence,Princeton University, based in China, categorised as academia,Academia.
When was FlexSBDD released?
FlexSBDD 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.
What is FlexSBDD used for?
FlexSBDD works in Biology, and is recorded as handling drug discovery. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
How much compute was used to train FlexSBDD?
Around 1.6 × 10¹⁹ 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.
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.