Luminous-supreme
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
- Aleph Alpha
- Organisation type
- Industry
- Country
- Germany
- Published
- 15 August 2022
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Language generation
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
- 70B
- Training data
- 1,069,300,000,000 tokens
"~70B"
from the table Total Size: 2.77 + 0.79 + 0.18 + 0.07 + 0.06 + 0.02 = 3.89 TB Tokens: 761.41B + 217.15B + 49.47B + 19.29B + 16.49B + 5.49B = 1069.30B 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
- 3.5 × 10²³ FLOP
- How it was established
- Hardware,Operation counting
"~839000h" GPU-hours on A100s, per Environmental Impact section of model card. 312 trillion * 839000 * 3600 * 0.3 = 2.8e23 6ND = 6*70B*1069.30B = 4.49106e+23 sqrt(2.8e23*4.49106e+23) = 3.54612... × 10^23 reported here: 167TFLOPS https://docs.aleph-alpha.com/docs/Deprecated%20Luminous/Deprecated-Luminous/model-card/
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 SXM4 40 GB,NVIDIA A100 SXM4 80 GB
- Chips used
- 512
- Wall-clock time
- 2,016 hours (84 days)
Approximately 12 weeks = 2016 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
- API access
- Training code
- Unreleased
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Likely above 10²³ FLOP
- Yes
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- Model Card Luminous
- Last updated
- 28 November 2025
What the numbers mean
Background
Luminous-supreme was published by Aleph Alpha, in Germany, in August 2022. industry is the category the publisher falls under.
It works in Language, and is recorded as doing language generation.
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 around 3.5 × 10²³ FLOP of arithmetic, on NVIDIA A100 SXM4 40 GB,NVIDIA A100 SXM4 80 GB, which is a statement about the training budget rather than about inference.
Around 1,069,300,000,000 tokens went into training it.
Answers
Luminous-supreme — common questions
What GPU do I need to run Luminous-supreme?
None. Luminous-supreme 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 Luminous-supreme open source?
No. Luminous-supreme has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does Luminous-supreme have?
Luminous-supreme has 70B parameters. "~70B". 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 Luminous-supreme?
Luminous-supreme was published by Aleph Alpha, based in Germany, categorised as industry.
When was Luminous-supreme released?
Luminous-supreme was published in August 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.
What is Luminous-supreme used for?
Luminous-supreme works in Language, and is recorded as handling language generation. These are the areas it was designed around; they describe intent rather than a hard boundary.
How much compute was used to train Luminous-supreme?
Around 3.5 × 10²³ FLOP, on NVIDIA A100 SXM4 40 GB,NVIDIA A100 SXM4 80 GB. 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.