AI models
OtterHD-8B
Parameters
8B
Published
Nov 7, 2023
OtterHD-8B is an AI model developed by Nanyang Technological University (Singapore), first published in November 2023. It works in the multimodal, vision and language domain, on tasks such as chat and visual question answering.
Epoch AI has no training-compute estimate for this model. The model has 8,000,000,000 parameters. It was trained on roughly 200.5M datapoints. Training ran on 8 NVIDIA A100 for about 9 hours.
It is built on top of Fuyu-8B. The reference paper has 85 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Nanyang Technological University
- Country of organization
- Singapore
- Domain
- Multimodal, Vision, Language
- Task
- Chat, Visual question answering
- Parameters
- 8,000,000,000
- Dataset size
- 200.5M
- Training hardware
- NVIDIA A100
- Chips used
- 8
- Training time
- 9 h
- Chip-hours
- 24
- Training power draw
- 6.3 kW
- Base model
- Fuyu-8B
- Citations
- 85
- Epoch confidence
- Confident
More from Nanyang Technological University
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