MiniMax-VL-01

Training compute

2.1×10²⁴ FLOP

Published

Jan 14, 2025

MiniMax-VL-01 is an AI model developed by MiniMax (China), first published in January 2025. It works in the vision, language and multimodal domain, on tasks such as visual question answering, language modeling/generation and question answering.

Training it took an estimated 2.1×10²⁴ FLOP of compute (estimation method: operation counting). Training ran on NVIDIA H800 SXM5.

Access: Open weights (restricted use). Its weights are openly available. It is built on top of MiniMax-Text-01. Epoch AI rates the confidence of this record as likely.

Full record

Organization: MiniMax
Country of organization: China
Domain: Vision, Language, Multimodal
Task: Visual question answering, Language modeling/generation, Question answering
Training compute: 2.1×10²⁴ FLOP
Compute estimation method: Operation counting
Training hardware: NVIDIA H800 SXM5
Model accessibility: Open weights (restricted use)
Open weights: Yes
Base model: MiniMax-Text-01
Epoch confidence: Likely