Crazy Stone

Closed weights INRIA May 2006

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
INRIA
Organisation type
Academia
Country
France
Published
29 May 2006
Authors
Rémi Coulom

What it does

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

Domain
Games
Task
Go

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
tokens

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
SOTA improvement

First ML model to use MCTS, plausibly it was SOTA for computer Go "The resulting algorithm was implemented in a 9 × 9 Go-playing program, Crazy Stone, that won the 10th KGS computer-Go tournament."

Record confidence
Unknown

Sources

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

Reference
Efficient selectivity and backup operators in Monte-Carlo tree search
Last updated
28 November 2025

What the numbers mean

About this model

Crazy Stone was published by INRIA, in France, in May 2006. It comes out of academia.

It works in Games, and is recorded as doing go.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

Training and provenance

It is tracked in the underlying dataset for one reason in particular: sOTA improvement.

Answers

Crazy Stone — common questions

01

Who created Crazy Stone?

Crazy Stone was published by INRIA, based in France, categorised as academia.

02

When was Crazy Stone released?

Crazy Stone was published in May 2006. 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 Crazy Stone used for?

Crazy Stone works in Games, and is recorded as handling go. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

04

What GPU do I need to run Crazy Stone?

None. Crazy Stone 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

Is Crazy Stone open source?

No. Crazy Stone has not had its weights published, so it exists only as a service controlled by its owner.

06

How many parameters does Crazy Stone have?

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

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.