AI models
DeepStack
Training compute
1.4×10¹⁹ FLOP
Parameters
2.5M
Published
Jan 6, 2017
DeepStack is an AI model developed by University of Alberta, Charles University and Czech Technical University (Canada and Czechia), first published in January 2017. It works in the games domain, on tasks such as poker.
Training it took an estimated 1.4×10¹⁹ FLOP of compute (estimation method: hardware). The model has 2,500,000 parameters. It was trained on roughly 25.4B datapoints.
The reference paper has 998 citations. Epoch AI rates the confidence of this record as speculative.
Full record
- Organization
- University of Alberta, Charles University, Czech Technical University
- Country of organization
- Canada, Czechia
- Domain
- Games
- Task
- Poker
- Training compute
- 1.4×10¹⁹ FLOP
- Compute estimation method
- Hardware
- Parameters
- 2,500,000
- Dataset size
- 25.4B
- Chips used
- 20
- Training time
- 218 h
- Chip-hours
- 4.4K
- Numerical format
- FP32
- Citations
- 998
- Epoch confidence
- Speculative
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models