Xiaomi releases MiMo-V2.5-Pro-FP4-DFlash, an FP4 model with block-diffusion decoding

Xiaomi MiMo has released MiMo-V2.5-Pro-FP4-DFlash, the FP4 backbone behind MiMo-V2.5-Pro-UltraSpeed, with MXFP4 quantization applied only to the MoE experts and a BF16 DFlash drafter for block-diffusion speculative decoding.

The backbone has 1.02T total and 42B active parameters, and the drafter proposes blocks of up to 8 tokens per forward pass. The release is supported in SGLang, with example launch commands provided.