iGPT-XL

Training compute

3.3×10²² FLOP

Parameters

6.8B

Published

Jun 17, 2020

iGPT-XL is an AI model developed by OpenAI (United States), first published in June 2020. It works in the vision and image generation domain, on tasks such as image completion. It counts among the frontier models: the systems trained with the most compute of their moment.

Training it took an estimated 3.3×10²² FLOP of compute (estimation method: third-party estimation). The model has 6,801,000,000 parameters. It was trained on roughly 4.7B datapoints. Training ran on NVIDIA Tesla V100 DGXS 32 GB. The compute alone is estimated at $101K in 2023 dollars.

Access: Open weights (unrestricted). Its weights are openly available. The reference paper has 1,694 citations. Epoch AI rates the confidence of this record as likely.

Full record

Organization: OpenAI
Country of organization: United States
Domain: Vision, Image generation
Task: Image completion
Training compute: 3.3×10²² FLOP
Compute estimation method: Third-party estimation
Parameters: 6,801,000,000
Dataset size: 4.7B
Training hardware: NVIDIA Tesla V100 DGXS 32 GB
Training cost (2023 USD): $101K
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Citations: 1,694
Epoch confidence: Likely