Xiaomi MiMo-V2.5

Headlines · 1

1. 8h
   Naive-N0.5-Flash open-weights coding model prioritizes speed

   NaiveAI released Naive-N0.5-Flash, an open-weights model for AI coding that continues training from Xiaomi’s MiMo-V2.5 and runs with the NaiveRT inference engine. Latent Space found that it answered faster overall than DeepSeek V4.1 Flash 1017 and GLM 5.3 Flash in limited tests, but it took longer on harder questions and had a slightly higher cost per question. NaiveAI reports about 984 tokens per second during thinking and 1,816 tokens per second while producing the answer, with a roughly 2,100-token-per-second peak measured on a single eight-GPU Blackwell node.

   Latent Space · 🔥 8

Experience and discussion from the community

Share my Xiaomi MiMo-V2.5 experienceAsk about Xiaomi MiMo-V2.5