Hosted on MSN
Xiaomi MiMo-V2.5-Pro gets UltraSpeed mode, breaks 1,000 tokens/second speed on standard GPUs
The MiMo-V2.5-Pro-UltraSpeed API is priced at 3x the standard rate. For reference, the regular MiMo-V2.5-Pro charges 0.025 yuan per million tokens on a cache hit, 3 yuan on a cache miss for input, and ...
Xiaomi‘s large language model family, MiMo, has officially launched UltraSpeed mode for MiMo-V2.5-Pro. Developed jointly with TileRT, the 1-trillion-parameter model can run on general-purpose GPUs ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results