Kimi K3 at 239 tokens/s！
Databricks is now #1 for Kimi K3 inference speed and latency on Artificial Analysis.
A huge 2.8T parameters model， it's the largest oss model we've ever served. We make sure the GPUs go brrr at Databricks.
AI 摘要
Kimi K3 达到 239 tokens/s！ 在 Artificial Analysis 上，Databricks 现已成为 Kimi K3 推理速度和延迟的第一名。 这是一个庞大的 2.8T 参数模型，也是我们服务过的最大开源模型。我们确保 GPU 在 Databricks 上全力运转。
Kimi K3 at 239 tokens/s！
Databricks is now #1 for Kimi K3 inference speed and latency on Artificial Analysis.
A huge 2.8T parameters model， it's the largest oss model we've ever served. We make sure the GPUs go brrr at Databricks.