China's Xiaomi MiMo Is Now 15X Faster Than ChatGPT and Claude (4 minute read) (opens in new tab)  🤖AI (Artificial Intelligence Research)

Xiaomi and inference partner TileRT have created a 1-trillion-parameter model, MiMo-V2.5-Pro-UltraSpeed, with an inference speed of 1,000 tokens per second on a standard 8-GPU commodity node. The speed was achieved through FP4 quantization on the model's expert layers and DFlash speculative decoding, which proposes a full block of tokens in one pass instead of one at a time. The model is available through a limited API trial from June 9 to June 23. It costs three times the standard MiMo-V2.5-...