AI models
Uni-Med
Training compute
1.4×10²³ FLOP
Parameters
8.8B
Published
Nov 1, 2024
Uni-Med is an AI model developed by Tsinghua University and Beijing University of Posts and Telecommunications (China), first published in November 2024.
Training it took an estimated 1.4×10²³ FLOP of compute. The model has 8,800,000,000 parameters. Training ran on 1 NVIDIA A800 SXM for about 10 hours.
Access: Unreleased. Its weights are not openly released. It is built on top of Llama 2-7B,ViT-G/14. The reference paper has 23 citations. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- Tsinghua University, Beijing University of Posts and Telecommunications
- Country of organization
- China
- Training compute
- 1.4×10²³ FLOP
- Parameters
- 8,800,000,000
- Training hardware
- NVIDIA A800 SXM
- Chips used
- 1
- Training time
- 10 h
- Training power draw
- 433 W
- Model accessibility
- Unreleased
- Open weights
- No
- Base model
- Llama 2-7B, ViT-G/14
- Citations
- 23
- 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