Libratus

Closed weights Carnegie Mellon University (CMU) August 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
Carnegie Mellon University (CMU)
Organisation type
Academia
Country
United States of America
Published
19 August 2017
Authors
N Brown, T Sandholm, S Machine

What it does

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

Domain
Games
Task
Poker

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

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
5.5 × 10²⁰ FLOP

"In total, Libratus used about 25 million core hours. Of those, about 13 million core hours were used for exploratory experiments and evaluation. About 6 million core hours were spent on the initial abstraction and equilibrium finding component, another 3 million were used for nested subgame solving, and about 3 million were used on the self-improvement algorithm." "Like many data-centric supercomputers, Bridges offers a relatively a modest number of FLOPS, but lots of memory: 895 teraflops and…

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.

Chip-hours
857,000

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

Claims to be first ML system to reach superhuman level at No Limit Poker Texas Hold Em "Heads-up nolimit Texas Hold’em has long been the primary benchmark challenge for imperfect-information games. In January 2017 Libratus beat a team of four top-10 headsup no-limit specialist professionals in a 120,000-hand 20-day Brains vs. AI challenge match. That is the first time an AI has beaten top humans in this game. Libratus beat the humans by a large margin (147 mbb/hand), with 99.98% statistical sig…

Record confidence
Likely
Citations
104

Sources

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

Reference
Libratus: The Superhuman AI for No-Limit Poker
Last updated
1 January 2026

What the numbers mean

Background

Libratus was published by Carnegie Mellon University (CMU), in United States of America, in August 2017. academia is the category the publisher falls under.

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

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

How it was trained

Producing it required around 5.5 × 10²⁰ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

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

Answers

Libratus — common questions

01

What is Libratus used for?

Libratus works in Games, and is recorded as handling poker. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

02

How much compute was used to train Libratus?

Around 5.5 × 10²⁰ FLOP. 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.

03

What GPU do I need to run Libratus?

None. Libratus 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.

04

Is Libratus open source?

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

05

How many parameters does Libratus have?

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

06

Who created Libratus?

Libratus was published by Carnegie Mellon University (CMU), based in United States of America, categorised as academia.

07

When was Libratus released?

Libratus was published in August 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.

Source

Original publication

Record last updated 1 January 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.