Wan 2.2 14B T2V

Training compute

4.2×10²³ FLOP

Parameters

14B

Published

Jul 28, 2025

Wan 2.2 14B T2V is an AI model developed by Alibaba (China), first published in July 2025. It works in the video domain, on tasks such as video generation and text-to-video.

Training it took an estimated 4.2×10²³ FLOP of compute (estimation method: operation counting). The model has 14,000,000,000 parameters. It was trained on roughly 5T datapoints.

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

Full record

Organization: Alibaba
Country of organization: China
Domain: Video
Task: Video generation, Text-to-video
Training compute: 4.2×10²³ FLOP
Compute estimation method: Operation counting
Parameters: 14,000,000,000
Dataset size: 5T
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Epoch confidence: Likely