MiniMax M3.1 Flash Launches with Day 0 SGLang Support, Exceeding 1000 tok/s

MiniMax partnered with SGLang, NVIDIA, AMD and RadixArk to deliver Day 0 production-ready support for MiniMax M3.1 Flash, achieving over 1000 tok/s single-request decoding and roughly 100K tok/s throughput per card across NVIDIA and AMD hardware.

2026-10-23 ~ 2026-10-24 · 2 related posts

• MiniMax M3.1 Flash hits >1K tok/s decode with day-0 SGLang support across NVIDIA and AMD — MiniMax_AI · 2026-10-23
• MiniMax M3.1 Flash tops 1K tok/s decode on SGLang, ~100K tok/s per GPU — ying11231 · 2026-10-24