Translated data: Xiaomi has released a large language model, MiLM-6B, with a parameter scale of 6.4 billion. This model has achieved the best results in its size category on C-Eval and CMMLU benchmarks. MiLM-6B not only performs exceptionally well in overall scores but also demonstrates excellent performance across various subjects and difficulty levels. This release further showcases Xiaomi's strategic layout and achievements in the field of AI large models.