Tagged with

2 articles found

Xiaomi’s 300B Model Just Got a Secret Speed Hack, DFlash Is the Real Deal

Xiaomi quietly dropped MiMo-V2.5-DFlash on Hugging Face. A 311B parameter model with block diffusion speculative decoding that could double your inference speed. Here’s what the community is finding.

#DFlash#LLM Inference#mimo...

agents

The Open Weights Kingpin Just Crushed Social Deduction Games

Xiaomi’s MiMo-V2.5-Pro doesn’t just crunch code, it outplays humans at complex social manipulation, and you can run it on your own hardware.

#agents#mimo#xiaomi