Allegro

Training compute

6.6×10²² FLOP

Parameters

3B

Published

Oct 20, 2024

Allegro is an AI model developed by Rhymes AI (United States), first published in October 2024. It works in the video domain, on tasks such as video generation and text-to-video.

Training it took an estimated 6.6×10²² FLOP of compute (estimation method: hardware). The model has 2,975,000,000 parameters. Training ran on 256 NVIDIA H100 SXM5 80GB.

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

Full record

Organization: Rhymes AI
Country of organization: United States
Domain: Video
Task: Video generation, Text-to-video
Training compute: 6.6×10²² FLOP
Compute estimation method: Hardware
Parameters: 2,975,000,000
Training hardware: NVIDIA H100 SXM5 80GB
Chips used: 256
Training power draw: 352.8 kW
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Epoch confidence: Speculative