DISTRO
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
- Nous Research
- Organisation type
- Industry
- Country
- United States of America
- Published
- 26 August 2024
- Authors
- Bowen Peng, Jeffrey Quesnelle, Dillon Rolnick, Ari Lotter, Umer H. Adil, Esteban La Rocca
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Language modeling/generation, Chat, Question answering
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
- 1.2B
- Training data
- 100,000,000,000 tokens
1.2B
Total Steps 25000 Sequence Length 2048 Batch Size 2048 (4M tokens) Total Tokens 104.8576B
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
- 7.1 × 10²⁰ FLOP
- How it was established
- Operation counting,Hardware
6 FLOP / parameter / token * 1.2*10^9 parameters * 104857600000 tokens = 7.5497472e+20 FLOP 989500000000000 FLOP / GPU / sec [bf16 assumed] *19.8 hours * 3600 sec / hour * 32 GPUs * 0.3 [assumed utilization] = 6.7710298e+20 FLOP sqrt(6.7710298e+20*7.5497472e+20) = 7.1497946e+20
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 H100 SXM5 80GB
- Chips used
- 32
- Wall-clock time
- 20 hours
- Power draw
- 44.2 kW
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
- A PRELIMINARY REPORT ON DISTRO
- Last updated
- 28 November 2025
What the numbers mean
What this model is
DISTRO was published by Nous Research, in United States of America, in August 2024. industry is the category the publisher falls under.
It works in Language, and is recorded as doing language modeling/generation, Chat, Question answering.
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 7.1 × 10²⁰ FLOP of arithmetic, on NVIDIA H100 SXM5 80GB, which is a statement about the training budget rather than about inference.
It was trained on about 100,000,000,000 tokens of text.
Answers
DISTRO — common questions
Who created DISTRO?
DISTRO was published by Nous Research, based in United States of America, categorised as industry.
When was DISTRO released?
DISTRO was published in August 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 DISTRO used for?
DISTRO works in Language, and is recorded as handling language modeling/generation, Chat, Question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.
How much compute was used to train DISTRO?
Around 7.1 × 10²⁰ FLOP, on NVIDIA H100 SXM5 80GB. 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 DISTRO?
None. DISTRO 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 DISTRO open source?
The licensing for DISTRO was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
How many parameters does DISTRO have?
DISTRO has 1.2B parameters. 1.2B. 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.
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.