GenCast

Training compute

8.2×10²⁰ FLOP

Published

May 1, 2024

GenCast is an AI model developed by Google DeepMind (United States), first published in May 2024. It works in the earth science domain, on tasks such as weather forecasting.

Training it took an estimated 8.2×10²⁰ FLOP of compute (estimation method: hardware). Training ran on 32 Google TPU v5e.

Access: Open weights (non-commercial). Its weights are openly available. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Google DeepMind
Country of organization: United States
Domain: Earth science
Task: Weather forecasting
Training compute: 8.2×10²⁰ FLOP
Compute estimation method: Hardware
Training hardware: Google TPU v5e
Chips used: 32
Chip-hours: 120
Training power draw: 14.2 kW
Model accessibility: Open weights (non-commercial)
Open weights: Yes
Epoch confidence: Confident