AI models
PaLI-3
Parameters
5B
Published
Oct 17, 2023
PaLI-3 is an AI model developed by Google DeepMind, Google Research and Google Cloud (United States), first published in October 2023. It works in the multimodal, language and vision domain, on tasks such as visual question answering, character recognition (ocr) and image captioning.
Epoch AI has no training-compute estimate for this model. The model has 5,000,000,000 parameters.
Access: Unreleased. Its weights are not openly released. It is built on top of UL2. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Google DeepMind, Google Research, Google Cloud
- Country of organization
- United States
- Domain
- Multimodal, Language, Vision
- Task
- Visual question answering, Character recognition (OCR), Image captioning
- Parameters
- 5,000,000,000
- Model accessibility
- Unreleased
- Open weights
- No
- Base model
- UL2
- 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