XiaomiMiMo/MiMo-V2-Flash

Xiaomi MiMo-V2-Flash is a proprietary MoE model developed by Xiaomi, designed for extreme inference efficiency with 309B total parameters (15B active). By incorporating an innovative Hybrid attention architecture and multi-layer MTP inference acceleration, it ranks among the top 2 global open-source models across multiple Agent benchmarks. Its coding capabilities surpass all open-source models and rival the industry-leading closed-source model, Claude 4.5 Sonnet—yet at only 2.5% of the inference cost and with 2x the generation speed, successfully pushing the limits of both model performance and efficiency.