MiMo-VL-7B-SFT

Training compute

1.2×10²⁴ FLOP

Parameters

7B

Published

Jun 4, 2025

MiMo-VL-7B-SFT is an AI model developed by Xiaomi Corp (China), first published in June 2025. It works in the vision, multimodal, language and video domain, on tasks such as character recognition (ocr), image captioning, language modeling/generation and 4 more.

Training it took an estimated 1.2×10²⁴ FLOP of compute (estimation method: operation counting). The model has 7,000,000,000 parameters. It was trained on roughly 2.4T datapoints.

Access: Open weights (unrestricted). Its weights are openly available. It is built on top of MiMo-7B-Base. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Xiaomi Corp
Country of organization: China
Domain: Vision, Multimodal, Language, Video
Task: Character recognition (OCR), Image captioning, Language modeling/generation, Question answering, Visual question answering, Video, Video description
Training compute: 1.2×10²⁴ FLOP
Compute estimation method: Operation counting
Parameters: 7,000,000,000
Dataset size: 2.4T
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Base model: MiMo-7B-Base
Epoch confidence: Confident