DiffBindFR
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
- Peking University,Tsinghua-Peiking Center for Life Sciences
- Organisation type
- Academia,Research collective
- Country
- China
- Published
- 9 April 2024
- Authors
- Jintao Zhu, Zhonghui Gu, Jianfeng Pei, Luhua Lai
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, Protein-ligand contact 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
Data points = 16,739 training structures Note: Epochs (1000) not counted as we only consider unique data points 16,739 = 1.674e4
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
- 4 × 10²⁰ FLOP
- How it was established
- Hardware
1. Hardware setup: - Main model: 8× NVIDIA A800 GPUs (7.80×10¹³ FLOP/s per GPU) - MDN model: 4× NVIDIA Tesla V100-SXM2 GPUs (1.25×10¹⁴ FLOP/s per GPU) 2. Training duration (estimated from steps and step time): - Main model: 262,000 steps × 5s = 1.31×10⁶ seconds (~15 days) - MDN model: 65,000 steps × 5s = 3.25×10⁵ seconds (~3.76 days) 3. Utilization rate: 40% 4. Final calculation: Main: 8 GPUs × 7.80×10¹³ FLOP/s × 1.31×10⁶ s × 0.4 = 3.31×10²⁰ FLOPs MDN: 4 GPUs × 1.25×10¹⁴ FLOP/s × 3.25×10⁵ s ×…
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
- Unreleased
BSD-3-Clause-Clear license https://github.com/HBioquant/DiffBindFR
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
- 16
Sources
Where this record came from and when it was last checked.
- Reference
- DiffBindFR: an SE(3) equivariant network for flexible protein–ligand docking
- Last updated
- 1 December 2025
What the numbers mean
Where it came from
DiffBindFR was published by Peking University,Tsinghua-Peiking Center for Life Sciences, in the country recorded as China, during April 2024. The category the publisher falls under is academia,Research collective.
It works in the domain of Biology, and is recorded as performing the task of protein-ligand binding affinity prediction, Protein-ligand contact 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
Training it took a computation budget of roughly 4 × 10²⁰ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
Answers
DiffBindFR — common questions
DiffBindFR— what is it used for?
It works in the domain of Biology, and is recorded as handling the task of protein-ligand binding affinity prediction, Protein-ligand contact prediction. These are the areas it was designed around; they describe intent rather than a hard boundary.
DiffBindFR— where can I download it?
The weights are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
DiffBindFR— how much compute was used to train it?
Training consumed around 4 × 10²⁰ 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.
DiffBindFR— what GPU do I need to run it?
We cannot say. It 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.
DiffBindFR— is it open source?
Its weights are published, so it 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.
DiffBindFR— how many parameters does it have?
No parameter count has been published for it, which is why no memory or speed figure appears on this page.
DiffBindFR— who created it?
It was published by Peking University,Tsinghua-Peiking Center for Life Sciences, based in China, an organisation categorised as academia,Research collective.
DiffBindFR— when was it released?
It was published in April 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.