IgGM
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
- Chinese Academy of Sciences,University of Chinese Academy of Sciences,Tencent
- Organisation type
- Academia,Academia,Industry
- Country
- China
- Published
- 22 September 2024
- Authors
- Rubo Wang, Fandi Wu, Xingyu Gao, Jiaxiang Wu, Peilin Zhao, Jianhua Yao
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Biology
- Task
- Protein design
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
- 15,506,880 tokens
Complexes: 6,448 + 1,907 = 8,355 Amino acids per complex: 450 + 350 + 300 = 1,100 Total amino acids: 8,355 * 1,100 = 9,190,500
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
- 8.6 × 10²⁰ FLOP
- How it was established
- Hardware
1. Hardware setup: 8x NVIDIA A100 SXM4 80GB GPUs, 3.12e14 FLOP/s per GPU 2. Training duration: Directly provided as 10 days = 864,000 seconds 3. Utilization rate: 40% 4. Final calculation: 3.12e14 FLOP/s × 864,000s × 0.4 × 8 GPUs = 8.6e20 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
- 8
- Wall-clock time
- 240 hours (10 days)
- Power draw
- 6.3 kW
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 (non-commercial)
- Training code
- Unreleased
PolyForm Noncommercial License 1.0.0 https://github.com/TencentAI4S/IgGM?tab=readme-ov-file
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
- IgGM: A Generative Model for Functional Antibody and Nanobody Design
- Last updated
- 28 November 2025
What the numbers mean
Background
IgGM was published by Chinese Academy of Sciences,University of Chinese Academy of Sciences,Tencent, in China, in September 2024. It comes out of academia,Academia,Industry.
It works in Biology, and is recorded as doing protein design.
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.
How it was trained
The training run consumed about 8.6 × 10²⁰ FLOP, on NVIDIA A100. That figure describes the cost of creating it and has no bearing on how quickly it generates text.
Around 15,506,880 tokens went into training it.
Answers
IgGM — common questions
Who created IgGM?
IgGM was published by Chinese Academy of Sciences,University of Chinese Academy of Sciences,Tencent, based in China, categorised as academia,Academia,Industry.
When was IgGM released?
IgGM 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 IgGM used for?
IgGM works in Biology, and is recorded as handling protein design. 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.
Where can I download IgGM?
The weights for IgGM are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
How much compute was used to train IgGM?
Around 8.6 × 10²⁰ 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.
What GPU do I need to run IgGM?
We cannot say. IgGM 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.
Is IgGM open source?
Its weights are published, so IgGM 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.
How many parameters does IgGM have?
No parameter count has been published for IgGM, which is why no memory or speed figure appears on this page.
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.