GPT3-6.7B (rerun of original)
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
- Microsoft,OpenAI
- Organisation type
- Industry,Industry
- Country
- United States of America
- Published
- 28 May 2020
- Authors
- Greg Yang, Edward J. Hu, Igor Babuschkin, Szymon Sidor, Xiaodong Liu, David Farhi, Nick Ryder, Jakub Pachocki, Weizhu Chen, Jianfeng Gao
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Language modeling/generation
- Numerical format
- FP32
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
- 6.7B
- Training data
- 300,000,000,000 tokens
- Epochs
- 1
6.7B
300B tokens (Figure 15) - same as original gpt-3 10K training steps
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
- 1.2 × 10²² FLOP
- How it was established
- Operation counting
6 FLOP / token / parameter * 6.7 * 10^9 parameters * 300 * 10^9 tokens = 1.206e+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 V100
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
repo here, don't think there's GPT-3 code though https://github.com/microsoft/mup/blob/main/README.md
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
- 262
- Benchmark data
- GPT3-6.7B (rerun of original)
Sources
Where this record came from and when it was last checked.
- Reference
- Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer
- Last updated
- 25 May 2026
What the numbers mean
About this model
GPT3-6.7B (rerun of original) was published by Microsoft,OpenAI, in the country recorded as United States of America, during May 2020. The category the publisher falls under is industry,Industry.
It works in the domain of Language, and is recorded as performing the task of language modeling/generation.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
How it was trained
Producing it required arithmetic totalling around 1.2 × 10²² FLOP, on hardware recorded as NVIDIA V100. That figure measures what producing the model cost, and has no bearing on how fast it answers.
Training consumed a corpus of around 300,000,000,000 tokens of text.
Answers
GPT3-6.7B (rerun of original) — common questions
GPT3-6.7B (rerun of original)— 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.
GPT3-6.7B (rerun of original)— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
GPT3-6.7B (rerun of original)— how many parameters does it have?
It has a parameter count of 6.7B. 6.7B. 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.
GPT3-6.7B (rerun of original)— who created it?
It was published by Microsoft,OpenAI, based in United States of America, an organisation categorised as industry,Industry.
GPT3-6.7B (rerun of original)— when was it released?
It was published in May 2020. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
GPT3-6.7B (rerun of original)— what is it used for?
It works in the domain of Language, and is recorded as handling the task of language modeling/generation. These are the areas it was designed around; they describe intent rather than a hard boundary.
GPT3-6.7B (rerun of original)— how much compute was used to train it?
Training consumed around 1.2 × 10²² FLOP, on hardware recorded as NVIDIA V100. 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.