Ep. 034 - Engrams: How DeepSeek Offloads KV Cache to DRAM and SSD (Core Research) | Jordan Nanos, Cam Quilici, Alec Ibarra, Bryan Shan

[about serving Kimi-K3 on a router] So, at 60% utilization, with 30% license fee that you have to give to moonshot, you can literally make a almost 50% profit margin serving this on GB300.

Semianalysis does paint a rosy picture of serving Kimi. They do preface this with "Until prices return to sane values" (or something like that, not verbatim)