MBP
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),Tencent,Zhejiang University (ZJU)
- Organisation type
- Academia,Industry,Academia
- Country
- China
- Published
- 11 December 2023
- Authors
- Jiaxian Yan, Zhaofeng Ye, Ziyi Yang, Chengqiang Lu, Shengyu Zhang, Qi Liu, Jiezhong Qiu
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- Protein-ligand binding affinity 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
- tokens
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
- 1.8 × 10¹⁸ FLOP
- How it was established
- Hardware
"We pre-trained our model on one NVIDIA A100-PCIE-40GB for about 16 h and fine-tuned for about 1 h." Assume 40% utilization and FP16 precision.
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
- Multi-task bioassay pre-training for protein-ligand binding affinity prediction
- Last updated
- 28 November 2025
What the numbers mean
What this model is
MBP was published by University of Science and Technology of China (USTC),Tencent,Zhejiang University (ZJU), in China, in December 2023. academia,Industry,Academia is the category the publisher falls under.
It works in Biology, and is recorded as doing protein-ligand binding affinity prediction.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
What went into building it
Producing it required around 1.8 × 10¹⁸ FLOP of arithmetic, which is a statement about the training budget rather than about inference.
Answers
MBP — common questions
What is MBP used for?
MBP works in Biology, and is recorded as handling protein-ligand binding affinity 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.
How much compute was used to train MBP?
Around 1.8 × 10¹⁸ FLOP. 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 MBP?
None. MBP 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 MBP open source?
The licensing for MBP 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 MBP have?
No parameter count has been published for MBP, which is why no memory or speed figure appears on this page.
Who created MBP?
MBP was published by University of Science and Technology of China (USTC),Tencent,Zhejiang University (ZJU), based in China, categorised as academia,Industry,Academia.
When was MBP released?
MBP was published in December 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.
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.