AI models
OpenFlamingo
Parameters
9B
Published
Aug 2, 2023
OpenFlamingo is an AI model developed by University of Washington, Stanford University, Allen Institute for AI, Hebrew University of Jerusalem, Columbia University, Google DeepMind and 2 more (United States, Israel and Germany), first published in August 2023. It works in the image generation domain, on tasks such as image generation and text-to-image.
Epoch AI has no training-compute estimate for this model. The model has 9,000,000,000 parameters. It was trained on roughly 17.4B datapoints. Training ran on 64 NVIDIA A100 SXM4 80 GB.
Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- University of Washington, Stanford University, Allen Institute for AI, Hebrew University of Jerusalem, Columbia University, Google DeepMind, University of California Santa Barbara (UCSB), Research Center Juelich
- Country of organization
- United States, Israel, Germany
- Domain
- Image generation
- Task
- Image generation, Text-to-image
- Parameters
- 9,000,000,000
- Dataset size
- 17.4B
- Training hardware
- NVIDIA A100 SXM4 80 GB
- Chips used
- 64
- Training power draw
- 50.9 kW
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Epoch confidence
- Confident
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