AlphaZero

Closed weights DeepMind December 2017

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
5 December 2017
Authors
David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, Timothy Lillicrap, Karen Simonyan, Demis Hassabis

What it does

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

Domain
Games
Task
Chess, Shogi, Go
Approach
Self-supervised learning

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.

Training data
3,520,000,000 tokens

"We trained a separate instance of AlphaZero for each game. Training proceeded for 700,000 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
1.1 × 10²⁰ FLOP

The Go version (there were versions trained individually for three different games) was trained for 34 hours using 5k TPUv1 for data generation 64 TPUv2 for parameter updating I used the PCD chip entries for the lowest precision numerical format we had for each, which was INT8 for TPUv1 and FP16 for TPUv2 Direct training compute: 1.06e20 FLOPs

How it was established
Third-party estimation

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 v2,Google TPU v1
Chips used
5,064
Wall-clock time
24 hours
Compute cost
$229,919

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.

Why it is tracked
Highly cited,Historical significance
Record confidence
Likely
Citations
2,071

Sources

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

Reference
Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
Last updated
25 May 2026

What the numbers mean

What this model is

AlphaZero was published by DeepMind, in the country recorded as United Kingdom of Great Britain and Northern Ireland, during December 2017. The publishing organisation is categorised as industry.

It works in the domain of Games, and is recorded as performing the task of chess, Shogi, Go.

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 1.1 × 10²⁰ FLOP, on hardware recorded as Google TPU v2,Google TPU v1. That figure measures what producing the model cost, and has no bearing on how fast it answers.

It was trained on a corpus of about 3,520,000,000 tokens of text.

The reason it appears in this catalogue at all: highly cited,Historical significance.

Answers

AlphaZero — common questions

01

AlphaZero— how much compute was used to train it?

Training consumed around 1.1 × 10²⁰ FLOP, on hardware recorded as Google TPU v2,Google TPU v1. 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.

02

AlphaZero— 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.

03

AlphaZero— is it open source?

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

04

AlphaZero— how many parameters does it have?

No parameter count has been published for it, which is why no memory or speed figure appears on this page.

05

AlphaZero— who created it?

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

06

AlphaZero— when was it released?

It was published in December 2017. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

07

AlphaZero— what is it used for?

It works in the domain of Games, and is recorded as handling the task of chess, Shogi, Go. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

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.