Gopher (280B)

Closed weights DeepMind 280B parameters December 2021

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
DeepMind
Organisation type
Industry
Country
United Kingdom of Great Britain and Northern Ireland
Published
8 December 2021
Authors
Jack W. Rae, Sebastian Borgeaud, Trevor Cai, Katie Millican, Jordan Hoffmann, Francis Song, John Aslanides, Sarah Henderson, Roman Ring, Susannah Young, Eliza Rutherford, Tom Hennigan, Jacob Menick, Albin Cassirer, Richard Powell, George van den Driessche, Lisa Anne Hendricks, Maribeth Rauh, Po-Sen Huang, Amelia Glaese, Johannes Welbl, Sumanth Dathathri, Saffron Huang, Jonathan Uesato, John Mellor…

What it does

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

Domain
Language
Task
Language modeling, Question answering
Approach
Self-supervised learning
Numerical format
BF16

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
280B

Language modelling provides a step towards intelligent communication systems by harnessing large repositories of written human knowledge to better predict and understand the world. In this paper, we present an analysis of Transformer-based language model performance across a wide range of model scales -- from models with tens of millions of parameters up to a 280 billion parameter model called Gopher. These models are evaluated on 152 diverse tasks, achieving state-of-the-art performance across …

Training data
300,000,000,000 tokens

"We train all models for 300 billion tokens with a 2048 token context window, using the Adam (Kingma and Ba, 2014) optimiser." 1 token ~ 0.75 words

Epochs
1
Batch size
6,000,000

Table 1. "Furthermore, we increase Gopher’s batch size from three to six million tokens per batch during training"

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
6.3 × 10²³ FLOP

Table A26 6.31E+08 Train PFLOPs

How it was established
Reported

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
Chips used
4,096
Chip-hours
3,768,320
Wall-clock time
920 hours (38.3 days)

"We trained Gopher for 920 hours in November and December 2020 in Google’s Georgia datacentre. The PUE of the datacenter at this time was 1.08; the net tCO2e per MWh in October 2020 was 0.33. Using an estimate of 283W drawn per chip, this leads to a total of 380 net tCO2e"

Hardware utilisation
MFU 37.8%

Compute used to train model (table A26): 6.31e23 Maximum possble compute based on GPU-hours at 100% utilization: 920 * 4096 * 3600 * 1.23e14 = 1.669e24 Therefore, we can calculate utilization: MFU = 6.31e23 / 1.669e24 = 0.3780

Power draw
3.7 MW
Compute cost
$640,617

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

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Frontier model
Yes
Likely above 10²³ FLOP
Yes
Why it is tracked
SOTA improvement

"These models are evaluated on 152 diverse tasks, achieving state-of-the-art performance across the majority"

Record confidence
Confident
Citations
1,605
Benchmark data
Gopher (280B)

Sources

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

Reference
"Scaling Language Models: Methods, Analysis & Insights from Training Gopher"
Last updated
25 May 2026

What the numbers mean

Background

Gopher (280B) was published by DeepMind, in the country recorded as United Kingdom of Great Britain and Northern Ireland, during December 2021. It comes out of an organisation categorised as industry.

It works in the domain of Language, and is recorded as performing the task of language modeling, Question answering.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

What went into building it

Training it took a computation budget of roughly 6.3 × 10²³ FLOP, on hardware recorded as Google TPU v3. That figure measures what producing the model cost, and has no bearing on how fast it answers.

The training set ran to roughly 300,000,000,000 tokens of text.

Its inclusion criterion: sOTA improvement.

Answers

Gopher (280B) — common questions

01

Gopher (280B)— when was it released?

It was published in December 2021. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

02

Gopher (280B)— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling, Question answering. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

03

Gopher (280B)— how much compute was used to train it?

Training consumed around 6.3 × 10²³ FLOP, on hardware recorded as 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.

04

Gopher (280B)— 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.

05

Gopher (280B)— is it open source?

No. Its weights have not been published, so it exists only as a service controlled by its owner.

06

Gopher (280B)— how many parameters does it have?

It has a parameter count of 280B. Language modelling provides a step towards intelligent communication systems by harnessing large repositories of written human knowledge to better predict and understand the world. In this paper, we present an analysis of Transformer-based language model performance across a wide range of model scales -- from models with tens of millions of parameters up to a 280 billion parameter model called Gopher. These models are evaluated on 152 diverse tasks, achieving state-of-the-art performance across the majority. Gains from scale are largest in areas such as reading comprehension, fact-checking, and the identification of toxic language, but logical and mathematical reasoning see less benefit. We provide a holistic analysis of the training dataset and model's behaviour, covering the intersection of model scale with bias and toxicity. Finally we discuss the application of language models to AI safety and the mitigation of downstream harms. 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.

07

Gopher (280B)— who created it?

It was published by DeepMind, based in United Kingdom of Great Britain and Northern Ireland, an organisation categorised as industry.

Source

Original publication

Record last updated 25 May 2026

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.