AI models
Ovis-7B
Training compute
1.7×10²³ FLOP
Parameters
7B
Published
Jun 17, 2024
Ovis-7B is an AI model developed by Alibaba and Nanjing University (China), first published in June 2024. It works in the multimodal, language and vision domain, on tasks such as visual question answering, language modeling/generation and question answering.
Training it took an estimated 1.7×10²³ FLOP of compute. The model has 7,000,000,000 parameters. Training ran on 128 NVIDIA H100 SXM5 80GB for about 15 hours.
Access: Open weights (unrestricted). Its weights are openly available. It is built on top of Qwen1.5-7B. The reference paper has 147 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Alibaba, Nanjing University
- Country of organization
- China
- Domain
- Multimodal, Language, Vision
- Task
- Visual question answering, Language modeling/generation, Question answering
- Training compute
- 1.7×10²³ FLOP
- Parameters
- 7,000,000,000
- Training hardware
- NVIDIA H100 SXM5 80GB
- Chips used
- 128
- Training time
- 15 h
- Training power draw
- 176.9 kW
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Base model
- Qwen1.5-7B
- Citations
- 147
- 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