GPT3-2.7B (FlashAttention-2)
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
- Stanford University,Princeton University
- Organisation type
- Academia,Academia
- Country
- United States of America
- Published
- 18 July 2023
- Authors
- Tri Dao
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Language modeling/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
- 2.7B
- Training data
- tokens
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 80 GB
- Chips used
- 8
- Hardware utilisation
- HFU 72.0%
- Power draw
- 6.4 kW
"We empirically validate that when used end-to-end to train GPT-style models, FlashAttention-2 reaches training speed of up to 225 TFLOPs/s per A100 GPU (72\% model FLOPs utilization)." Seems to be a test of FlashAttention2. It's also describing HFU, not MFU. HFU = 0.7200
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
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Why it is tracked
- Highly cited,Historical significance
- Record confidence
- Confident
- Citations
- 2,682
Sources
Where this record came from and when it was last checked.
- Reference
- FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
- Last updated
- 25 May 2026
What the numbers mean
Where it came from
GPT3-2.7B (FlashAttention-2) was published by Stanford University,Princeton University, in United States of America, in July 2023. academia,Academia is the category the publisher falls under.
It works in Language, and is recorded as doing 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
It is tracked in the underlying dataset for one reason in particular: highly cited,Historical significance.
Answers
GPT3-2.7B (FlashAttention-2) — common questions
Who created GPT3-2.7B (FlashAttention-2)?
GPT3-2.7B (FlashAttention-2) was published by Stanford University,Princeton University, based in United States of America, categorised as academia,Academia.
When was GPT3-2.7B (FlashAttention-2) released?
GPT3-2.7B (FlashAttention-2) 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 GPT3-2.7B (FlashAttention-2) used for?
GPT3-2.7B (FlashAttention-2) works in Language, and is recorded as handling language modeling/generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
What GPU do I need to run GPT3-2.7B (FlashAttention-2)?
None. GPT3-2.7B (FlashAttention-2) 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 GPT3-2.7B (FlashAttention-2) open source?
No. GPT3-2.7B (FlashAttention-2) has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does GPT3-2.7B (FlashAttention-2) have?
GPT3-2.7B (FlashAttention-2) has 2.7B 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.
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.