GraSR
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
- Shanghai Jiao Tong University,Ministry of Education of China
- Organisation type
- Academia,Government
- Country
- China
- Published
- 24 March 2022
- Authors
- Chunqiu Xia, Shi-Hao Feng, Ying Xia, Xiaoyong Pan, Hong-Bin Shen
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- 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
- 13,265 tokens
SCOPe v2.07 Dataset: Total PDB Entries: 87,224 Total Domains: 276,231 Training Set Size = Total Domains - Cross-Validation Domains Training Set Size = 276,231 - 13,265 = 262,966 domains
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
- 3.8 × 10¹⁸ FLOP
- How it was established
- Hardware
1. Hardware setup: 2x TITAN Xp GPUs (1.10×10¹³ FLOP/s each) 2. Training duration: Estimated 5 days (432,000 seconds) based on "several days" mention -> "Likely" confidence 3. Utilization rate: 40% 4. Calculation: 2 GPUs × 1.10×10¹³ FLOP/s × 432,000s × 0.40 = 3.8×10¹⁸ 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 TITAN Xp
- Chips used
- 2
- Wall-clock time
- 120 hours
- Power draw
- 1.0 kW
"The whole GraSR model is trained on two TITAN Xp Graphics Cards, and the training procedure took several days." Estimated 5 days (432,000 seconds) based on "several days" mention
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 (non-commercial)
The data and source code can be found at https://github.com/chunqiux/GraSR (GPL-3.0 license). In addition, we also archive it on Zenodo (https://doi.org/10.5281/zenodo.5338957). "The GraSR parameters are made availabe under a Creative Commons Attribution 4.0 International License."
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Likely
- Citations
- 28
Sources
Where this record came from and when it was last checked.
- Reference
- Fast protein structure comparison through effective representation learning with contrastive graph neural networks
- Last updated
- 1 January 2026
What the numbers mean
Where it came from
GraSR was published by Shanghai Jiao Tong University,Ministry of Education of China, in the country recorded as China, during March 2022. The category the publisher falls under is academia,Government.
It works in the domain of Biology, and is recorded as performing the task of protein structure comparison.
The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.
What went into building it
The training run consumed about 3.8 × 10¹⁸ FLOP, on hardware recorded as NVIDIA TITAN Xp. That figure measures what producing the model cost, and has no bearing on how fast it answers.
The training set ran to roughly 13,265 tokens of text.
Answers
GraSR — common questions
GraSR— 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.
GraSR— how much compute was used to train it?
Training consumed around 3.8 × 10¹⁸ FLOP, on hardware recorded as NVIDIA TITAN Xp. 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.
GraSR— 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.
GraSR— 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.
GraSR— 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.
GraSR— who created it?
It was published by Shanghai Jiao Tong University,Ministry of Education of China, based in China, an organisation categorised as academia,Government.
GraSR— when was it released?
It was published in March 2022. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
GraSR— what is it used for?
It works in the domain of Biology, and is recorded as handling the task of protein structure comparison. These are the areas it was designed around; they describe intent rather than a hard boundary.
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.