CLAY
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
- Shanghai Tech University,Deemos Technology,Huazhong University of Science and Technology
- Organisation type
- Academia,Industry,Academia
- Country
- China
- Published
- 30 May 2024
- Authors
- Longwen Zhang, Ziyu Wang, Qixuan Zhang, Qiwei Qiu, Anqi Pang, Haoran Jiang, Wei Yang, Lan Xu, Jingyi Yu
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- 3D modeling, Vision
- Task
- 3D reconstruction
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.
- Parameters
- 1.5B
- Training data
- tokens
"a refined collection of 527K objects from ShapeNet and Objaverse"
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
- 3.1 × 10²² FLOP
- How it was established
- Hardware
312000000000000 FLOP / GPU / sec [A800 reported] * 256 GPUs * 360 hours * 3600 sec / hour * 0.3 [assumed utilization] = 3.1054234e+22 FLOP
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 A800 PCIe
- Chips used
- 256
- Wall-clock time
- 360 hours (15 days)
"Our largest model, the XL, was trained on a cluster of 256 NVidia A800 GPUs, for approximately 15 days, with progressive training." 15 days = 360 hours
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
- Closed — provider access only
- Model access
- Unreleased
- Training code
- Unreleased
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
- CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets
- Last updated
- 28 November 2025
What the numbers mean
What this model is
CLAY was published by Shanghai Tech University,Deemos Technology,Huazhong University of Science and Technology, in the country recorded as China, during May 2024. The category the publisher falls under is academia,Industry,Academia.
It works in the domain of 3D modeling, Vision, and is recorded as performing the task of 3D reconstruction.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
How it was trained
Producing it required arithmetic totalling around 3.1 × 10²² FLOP, on hardware recorded as NVIDIA A800 PCIe. That figure measures what producing the model cost, and has no bearing on how fast it answers.
Answers
CLAY — common questions
CLAY— what GPU do I need to run it?
None. This 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.
CLAY— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
CLAY— how many parameters does it have?
It has a parameter count of 1.5B. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.
CLAY— who created it?
It was published by Shanghai Tech University,Deemos Technology,Huazhong University of Science and Technology, based in China, an organisation categorised as academia,Industry,Academia.
CLAY— when was it released?
It was published in May 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.
CLAY— what is it used for?
It works in the domain of 3D modeling, Vision, and is recorded as handling the task of 3D reconstruction. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
CLAY— how much compute was used to train it?
Training consumed around 3.1 × 10²² FLOP, on hardware recorded as NVIDIA A800 PCIe. 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.