Xiaomi MiMo and TileRT Push a 1-Trillion-Parameter Model Past 1000 Tokens Per Second on Commodity GPUs
AI disclosure
Summary
<p>Xiaomi's MiMo team, with TileRT, released MiMo-V2.5-Pro-UltraSpeed, a serving mode for the MiMo-V2.5-Pro model. It decodes over 1000 tokens per second on a 1-trillion-parameter model using a single 8-GPU commodity node.</p> <p>The post <a href="https://www.marktechpost.com/2026/06/08/xiaomi-mimo-and-tilert-push-a-1-trillion-parameter-model-past-1000-tokens-per-second-on-commodity-gpus/">Xiaomi MiMo and TileRT Push a 1-Trillion-Parameter Model Past 1000 Tokens Per Second on Commodity GPUs</a> appeared first on <a href="https://www.marktechpost.com">MarkTechPost</a>.</p>