MiMo-V2.5 is an open-source multimodal AI model hosted on Hugging Face, supporting local inference for tasks involving text, images, audio, and video. It is designed for researchers and developers seeking accessible, open-weight AI models for experimentation and deployment.
MiMo sits in PulseGate's Multimodal & vision category. It focuses on providing an open-source multimodal AI model for local inference and research. It is built as an open-source project for AI researchers and developers. The project is open source (Apache-2.0). It runs on the command line.
Behind MiMo is XiaomiMiMo, and it first shipped in 2025. The project is developed in the open on GitHub with 1.4k stars. Key capabilities include multimodal inference, open weights, and local deployment.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do