AI models
Unified-IO (XL)
Training compute
3.5×10²¹ FLOP
Parameters
2.9B
Published
Jun 17, 2022
Unified-IO (XL) is an AI model developed by Allen Institute for AI and University of Washington (United States), first published in June 2022. It works in the multimodal, vision and language domain, on tasks such as object detection, language modeling/generation, image generation and 6 more.
Training it took an estimated 3.5×10²¹ FLOP of compute (estimation method: operation counting). The model has 2,925,000,000 parameters. It was trained on roughly 74.9B datapoints. Training ran on Google TPU v4.
Access: Open weights (unrestricted). Its weights are openly available. The reference paper has 513 citations. Epoch AI rates the confidence of this record as speculative.
Full record
- Organization
- Allen Institute for AI, University of Washington
- Country of organization
- United States
- Domain
- Multimodal, Vision, Language
- Task
- Object detection, Language modeling/generation, Image generation, Visual question answering, Image classification, Image captioning, Text classification, Text summarization, Question answering
- Training compute
- 3.5×10²¹ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 2,925,000,000
- Dataset size
- 74.9B
- Training hardware
- Google TPU v4
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Citations
- 513
- Epoch confidence
- Speculative
More from Allen Institute for AI,University of Washington
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