Back to events
Open-source releaseLimited global significanceConfirmed confidence

Xiaomi releases MiMo VL 7B

Xiaomi releases the SFT and RL versions of the open MiMo VL 7B vision-language model for general visual understanding and multimodal reasoning.

Event details

Xiaomi released the SFT and RL versions of MiMo VL 7B on June 4, 2025 for general visual understanding and multimodal reasoning. The model has 7B parameters, is open source and is classified as an autoregressive Transformer; the MiMo-VL technical report is the primary source.

Why it matters

An open-source model release with a documented model family, parameter scale or access condition.

39/100Global significance score. Regional effects are recorded only when the evidence supports a meaningful difference.

Access notes

Publicly available as an open-source model.