Xiaomi releases MiMo-V2.5, an open omnimodal model with 1M context
Original titleXiaomiMiMo/MiMo-V2.5
AISummary
Xiaomi's MiMo-V2.5 is a native omnimodal model that understands text, image, video, and audio within one architecture. It is a sparse MoE with 310B total and 15B activated parameters, and supports up to 1M tokens of context. The repository also notes a config.json and tokenizer_config.json update that users who downloaded before commit 4da2748 should re-pull.
AIWhy it matters
The repository documents a 310B-parameter omnimodal MoE with a hybrid attention design, useful for comparing long-context efficiency against other open multimodal models.
Source: Xiaomi MiMo · new models on Hugging Face · huggingface.co