SmooCT
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 College London (UCL)
- Organisation type
- Academia
- Country
- United Kingdom of Great Britain and Northern Ireland
- Published
- 1 July 2014
- Authors
- Johannes Heinrich, David Silver
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
"Each three-player agentwas trained for about 12 billion episodes" An episode seems to be a round of betting.
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
- 6.9 × 10¹⁶ FLOP
- How it was established
- Hardware
"Each three-player agent was trained for about 12 billion episodes, requiring about 48 hours of training time [...] on a modern computer without using parallelization" Assume an Intel i7 so 400e9 FLOP/s. 6.9e16 = 400e9*60*60*48
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Wall-clock time
- 48 hours
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
- Record confidence
- Likely
- Citations
- 16
First RL system to achieve superhuman level at Poker Limit Texas Hold Em
Sources
Where this record came from and when it was last checked.
- Reference
- Self-Play Monte-Carlo Tree Search in Computer Poker
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
SmooCT was published by University College London (UCL), in United Kingdom of Great Britain and Northern Ireland, in July 2014. 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
The training run consumed about 6.9 × 10¹⁶ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.
It is tracked in the underlying dataset for one reason in particular: sOTA improvement.
Answers
SmooCT — common questions
How much compute was used to train SmooCT?
Around 6.9 × 10¹⁶ 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.
What GPU do I need to run SmooCT?
None. SmooCT 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.
Is SmooCT open source?
The licensing for SmooCT was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
How many parameters does SmooCT have?
No parameter count has been published for SmooCT, which is why no memory or speed figure appears on this page.
Who created SmooCT?
SmooCT was published by University College London (UCL), based in United Kingdom of Great Britain and Northern Ireland, categorised as academia.
When was SmooCT released?
SmooCT was published in July 2014. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is SmooCT used for?
SmooCT 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.
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.