DeepStack

Closed weights University of Alberta,Charles University,Czech Technical University 2.5M parameters January 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
University of Alberta,Charles University,Czech Technical University
Organisation type
Academia,Academia,Academia
Country
Canada, Czechia
Published
6 January 2017
Authors
Matej Moravčík, Martin Schmid, Neil Burch, Viliam Lisý, Dustin Morrill, Nolan Bard, Trevor Davis, Kevin Waugh, Michael Johanson, Michael Bowling

What it does

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

Domain
Games
Task
Poker
Numerical format
FP32

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
2.5M

Figure 3, p.9 source: https://docs.google.com/spreadsheets/d/1Kj4Q5WADcDXtUJLIOfGTCE3tGvxNczEMwyy8QtgSkHk/edit#gid=54587040&fvid=1361937389

Training data
25,380,000,000 tokens

"The turn network was trained by solving 10 million randomly generated poker turn games. These turn games used randomly generated ranges, public cards, and a random pot size (10)."

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
1.4 × 10¹⁹ FLOP

The largest source of compute necessary for training seems to be the data generation job on 20 GPUs. We count this towards the training compute because it requires simulation using the network. This is analogous to the AlphaGo systems simulating Go games. From p.26: "For the flop network, one million poker flop situations (from after the flop cards are dealt) were generated and solved. These situations were solved using DeepStack’s depth limited solver with the turn network used for the counter…

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.

Chips used
20
Chip-hours
4,368
Wall-clock time
218 hours (9.1 days)

from compute notes - around 9 days - half a year of GPU compute using 20 GPUs

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 human-competitive poker AI, confirmed by website: https://www.deepstack.ai/

Record confidence
Speculative
Citations
998

Sources

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

Reference
DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker
Last updated
25 May 2026

What the numbers mean

About this model

DeepStack was published by University of Alberta,Charles University,Czech Technical University, in Canada, in January 2017. It comes out of academia,Academia,Academia.

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

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

What went into building it

The training run consumed about 1.4 × 10¹⁹ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

It was trained on about 25,380,000,000 tokens of text.

The reason it appears in this catalogue at all is sOTA improvement.

Answers

DeepStack — common questions

01

How many parameters does DeepStack have?

DeepStack has 2.5M parameters. Figure 3, p.9 source: https://docs.google.com/spreadsheets/d/1Kj4Q5WADcDXtUJLIOfGTCE3tGvxNczEMwyy8QtgSkHk/edit#gid=54587040&fvid=1361937389. 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.

02

Who created DeepStack?

DeepStack was published by University of Alberta,Charles University,Czech Technical University, based in Canada, categorised as academia,Academia,Academia.

03

When was DeepStack released?

DeepStack was published in January 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.

04

What is DeepStack used for?

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

05

How much compute was used to train DeepStack?

Around 1.4 × 10¹⁹ 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.

06

What GPU do I need to run DeepStack?

None. DeepStack 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.

07

Is DeepStack open source?

The licensing for DeepStack was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

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.