XiaomiMiMo / MiMo-V2.5
Agents311B102.9K433Updated Oct 28, 2026
Downloads
102.9K
Likes
433
Last updated
Oct 28, 2026
License
mit
MiMo-V2.5 is a native omnimodal model with strong agentic capabilities, supporting text, image, video, and audio understanding within a unified architecture. Built upon the MiMo-V2-Flash backbone and extended with dedicated vision and audio encoders, it delivers robust perform…
Tasks & library
- text generation
- transformers
Tags
- transformers
- mimo_v2
- text-generation
- multimodal
- vision-language
- audio
Technical specifications
Parameters311B
Librarytransformers
Languagesen, zh
Licensemit