Kimi K3
on 16× NVIDIA DGX Spark · vLLM
Summary
User reports the full Kimi K3 model running on a 16x DGX Spark cluster at an average of 20+ t/s, peaking at 38 t/s, with prefill at 750 t/s.
This is a first run, and the user plans to optimize and publish a vLLM image.