llamaperf

Kimi K2.6

Moonshot AI · 1 report

Thin page (1 of 3 reports needed for indexing). Add yours.
reported speed:
9.7 tokens/s generation · 264.0 tokens/s prompt processing

Reported by the source; GPU count, offloading and concurrent requests can change this figure. Check the full setup before comparing.

User reports Kimi K2.6 at 264 t/s prompt processing and 9.7 t/s generation on 32x AMD MI50 32GB GPUs.

May 1, 2026