MiniMax (official)@MiniMax_AI · XAI 摘要
M3 正在与 @togethercompute 携手运行 🤝，推理速度比以往更快。MiniMax-M3 是开源权重的原生多模态模型，支持 1M 上下文、稀疏注意力和思考/非思考模式，Together AI 推理优化带来高达 125% 的吞吐量提升。
M3 is running together 🤝 with @togethercompute， and with faster-than-ever inference
MiniMax-M3 from @MiniMax_AI is now available on Together AI. It's an open-weight native multimodal model with 1M context, MiniMax Sparse Attention, and thinking...