ChatGLM3-6B

Training compute

5×10²² FLOP

Parameters

6B

Published

Oct 27, 2023

ChatGLM3-6B is an AI model developed by Z.ai (Zhipu AI) (China), first published in October 2023. It works in the multimodal, language and vision domain, on tasks such as chat, visual question answering and code generation.

Training it took an estimated 5×10²² FLOP of compute (estimation method: operation counting). The model has 6,000,000,000 parameters. It was trained on roughly 1.4T datapoints.

Access: Open weights (restricted use). Its weights are openly available. Epoch AI rates the confidence of this record as speculative.

Full record

Organization: Z.ai (Zhipu AI)
Country of organization: China
Domain: Multimodal, Language, Vision
Task: Chat, Visual question answering, Code generation
Training compute: 5×10²² FLOP
Compute estimation method: Operation counting
Parameters: 6,000,000,000
Dataset size: 1.4T
Model accessibility: Open weights (restricted use)
Open weights: Yes
Epoch confidence: Speculative