MiMo-V2.5-Pro-UltraSpeed

MiMo-V2.5-Pro-UltraSpeed is an advanced AI language model developed by Xiaomi, capable of generating up to 1,200 tokens per second on a 1-trillion-parameter model. This performance is achieved through a deep collaboration with TileRT, focusing on extreme model-system co-design to optimize inference speed on commodity GPUs.

MiMo-V2.5-Pro-UltraSpeed is an advanced AI language model developed by Xiaomi, capable of generating up to 1,200 tokens per second on a 1-trillion-parameter model. This performance is achieved through a deep collaboration with TileRT, focusing on extreme model-system co-design to optimize inference speed on commodity GPUs.

• 01Generates up to 1,200 tokens per second on a 1-trillion-parameter model
• 02Achieves high inference speed on commodity GPUs through model-system co-design
• 03Utilizes FP4 quantization and DFlash speculative decoding for enhanced performance
• 04Available through a limited-time application-based API from June 9 to June 23, 2026
• 05Offers free Chat access to approved users during the trial period
• 06Enables real-time decision-making in critical scenarios