LM-Design
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
- ByteDance,University of Wisconsin Madison
- Organisation type
- Industry,Academia
- Country
- China, United States of America
- Published
- 23 July 2023
- Authors
- Zaixiang Zheng, Yifan Deng, Dongyu Xue, Yi Zhou, Fei Ye, Quanquan Gu
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.
- Parameters
- 6.9M
- Training data
- 811,080 tokens
"That is because LMDESIGN has 6.9M parameters while ProteinMPNN+CMLM only has 1.6M parameters."
Total tokens = Number of Sequences × Average Sequence Length Total tokens = 50,000,000 × 300 = 1.5 × 10^10 tokens Final estimate: 1.5e10 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
- 1.4 × 10²⁰ FLOP
- How it was established
- Hardware
1. Hardware setup: 8x NVIDIA V100 GPUs (1.25 x 10^14 FLOP/s per GPU) 2. Training duration: 4 days (345,600 seconds) - estimated based on 10 epochs over 50M sequences with 6000 residues per batch 3. Utilization rate: 40% 4. Final calculation: (1.25 x 10^14 FLOP/s/GPU × 8 GPUs) × 345,600 seconds × 0.4 = 1.4 x 10^20 FLOPs
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
- Citations
- 46
Sources
Where this record came from and when it was last checked.
- Reference
- Structure-informed Language Models Are Protein Designers
- Last updated
- 28 November 2025
What the numbers mean
What this model is
LM-Design was published by ByteDance,University of Wisconsin Madison, in China, in July 2023. The organisation is categorised as industry,Academia.
It works in Biology, and is recorded as doing protein design.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
How it was trained
The training run consumed about 1.4 × 10²⁰ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.
It was trained on about 811,080 tokens of text.
Answers
LM-Design — common questions
What GPU do I need to run LM-Design?
None. LM-Design 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 LM-Design open source?
No. LM-Design has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does LM-Design have?
LM-Design has 6.9M parameters. "That is because LMDESIGN has 6.9M parameters while ProteinMPNN+CMLM only has 1.6M parameters.". 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.
Who created LM-Design?
LM-Design was published by ByteDance,University of Wisconsin Madison, based in China, categorised as industry,Academia.
When was LM-Design released?
LM-Design was published in July 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.
What is LM-Design used for?
LM-Design works in Biology, and is recorded as handling protein design. These are the areas it was designed around; they describe intent rather than a hard boundary.
How much compute was used to train LM-Design?
Around 1.4 × 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.
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.