Report
MiniMax M3.1 Flash 428B is out, with an open-source DFlash 2 drafter
NVIDIA says Vera Rubin offers Day 0 support for the model, with throughput of up to 200K TPS/GPU.
TLDR
NVIDIA says MiniMax M3.1 Flash 428B is built for everyday coding and agents. It claims Vera Rubin offers Day 0 support, with up to 200K TPS/GPU and more than 700 TPS/user. inco_ai says it open-sourced a DFlash 2 drafter for the model under Apache 2.0, claiming it makes generation up to 3.5× faster without loss.
Combined views
8.2K
13 Sources, first seen ago
