Artificial Analysis· @ArtificialAnlys · X·· 3 小时前AI 评分50
AI 导读
Kimi K3 是我们收录的最大模型，总参数 2.8T，激活参数 104B。MI355X 在每用户 50 tok/s 下每 MW 约服务 8M tokens/s，约为 B300（约 24M）的三分之一，后者采用 NVIDIA 的多节点解耦配置。其曲线较平缓，在每用户 12 tok/s 时峰值约为 13M；对于单个智能体，它达到 152 tok/s，而 B300 为 235。
正文
Kimi K3 is the largest model we feature, with 2.8T total and 104B active parameters. MI355X serves ~8M tokens/s per MW at 50 tok/s per user, about a third of B300 (~24M), which uses NVIDIA's multi-node disaggregated configs. Its curve is shallow, peaking at about 13M at 12 tok/s per user, and for a single agent it reaches 152 tok/s against 235 on B300.
来源：Artificial Analysis · x.com