AI models
GLM-10B
Training compute
4.9×10²¹ FLOP
Parameters
10B
Published
Mar 18, 2021
GLM-10B is an AI model developed by Tsinghua University, Beijing Academy of Artificial Intelligence / BAAI, Massachusetts Institute of Technology (MIT) and Shanghai Qi Zhi institute (China and United States), first published in March 2021. It works in the language domain, on tasks such as language modeling/generation.
Training it took an estimated 4.9×10²¹ FLOP of compute (estimation method: hardware,operation counting). The model has 10,000,000,000 parameters. Training ran on 64 NVIDIA V100 for about 1.8K hours.
Access: Open weights (unrestricted). Its weights are openly available. The reference paper has 1,919 citations. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- Tsinghua University, Beijing Academy of Artificial Intelligence / BAAI, Massachusetts Institute of Technology (MIT), Shanghai Qi Zhi institute
- Country of organization
- China, United States
- Domain
- Language
- Task
- Language modeling/generation
- Training compute
- 4.9×10²¹ FLOP
- Compute estimation method
- Hardware, Operation counting
- Parameters
- 10,000,000,000
- Training hardware
- NVIDIA V100
- Chips used
- 64
- Training time
- 1,791 h
- Training power draw
- 38.9 kW
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Citations
- 1,919
- 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