Artificial Analysis· @ArtificialAnlys · X·· 3 小时前AI 评分53
AI 导读
Artificial Analysis 指出 Kimi K3 是其收录的最大模型，总参数 2.8T、激活参数 104B。在 MI355X 上每兆瓦约 8M tokens/s（单用户 50 tok/s），约为 B300（约 24M）的三分之一，后者使用 NVIDIA 多节点解耦配置。其曲线较平缓，在单用户 12 tok/s 时峰值约 13M；单智能体场景下达到 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