GQA-8-XXL

Closed weights Google Research 11B parameters December 2023

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
Google Research
Organisation type
Industry
Country
United States of America
Published
23 December 2023
Authors
Joshua Ainslie, James Lee-Thorp, Michiel de Jong, Yury Zemlyanskiy, Federico Lebrón, Sumit Sanghai

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Language
Task
Text summarization, Language modeling/generation, Translation
Base model
T5-11B

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
11B

same as base model

Training data
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 × 10²² FLOP

3.3e+22 FLOP [base model] + 1.912896e+21 FLOP = 3.4912896e+22 FLOP

How it was established
Hardware

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
Google TPU v3
Chip-hours
14,400

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
Open source

Apache 2.0 https://github.com/google/flaxformer

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
Historical significance

the paper introduced grouped-query attention

Record confidence
Confident

Sources

Where this record came from and when it was last checked.

Reference
GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints
Last updated
28 November 2025

What the numbers mean

Background

GQA-8-XXL was published by Google Research, in United States of America, in December 2023. The organisation is categorised as industry.

It works in Language, and is recorded as doing text summarization, Language modeling/generation, Translation.

It is derived from T5-11B rather than trained from scratch, which is the usual way a specialised model is produced.

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 × 10²² FLOP of arithmetic, on Google TPU v3, which is a statement about the training budget rather than about inference.

It is tracked in the underlying dataset for one reason in particular: historical significance.

Answers

GQA-8-XXL — common questions

01

Who created GQA-8-XXL?

GQA-8-XXL was published by Google Research, based in United States of America, categorised as industry.

02

When was GQA-8-XXL released?

GQA-8-XXL was published in December 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.

03

What is GQA-8-XXL used for?

GQA-8-XXL works in Language, and is recorded as handling text summarization, Language modeling/generation, Translation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

04

How much compute was used to train GQA-8-XXL?

Around 3.5 × 10²² FLOP, on Google TPU v3. 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.

05

What GPU do I need to run GQA-8-XXL?

None. GQA-8-XXL 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.

06

Is GQA-8-XXL open source?

No. GQA-8-XXL has not had its weights published, so it exists only as a service controlled by its owner.

07

How many parameters does GQA-8-XXL have?

GQA-8-XXL has 11B parameters. same as base model. 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.

Source

Original publication

Record last updated 28 November 2025

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.