AI models
Pix2Struct-Large
Training compute
1.7×10²⁰ FLOP
Parameters
1.3B
Published
Jun 15, 2023
Pix2Struct-Large is an AI model developed by Google Research and University of Cambridge (United States and United Kingdom), first published in June 2023. It works in the vision domain, on tasks such as image captioning and visual question answering.
Training it took an estimated 1.7×10²⁰ FLOP of compute (estimation method: operation counting). The model has 1,300,000,000 parameters.
Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- Google Research, University of Cambridge
- Country of organization
- United States, United Kingdom
- Domain
- Vision
- Task
- Image captioning, Visual question answering
- Training compute
- 1.7×10²⁰ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 1,300,000,000
- Chips used
- 128
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Epoch confidence
- Likely
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