Kimi K3 2780B (104B active) REAP73
on M3 Ultra 512GB · mlx-lm · 1,000,000 ctx
Use cases
multilingualcodingvisionlong-context
Summary
User reports Kimi K3 REAP73 at 5.51 t/s on a 512 GiB M3 Ultra.
Setup is mlx-lm with mxfp4 experts and Q8 non-experts, 242 of 896 experts retained, single machine.
Figures are the mean of three prompts x 96 tokens; the 350 GB REAP80 build decodes at 5.54 t/s and the graded two-bank build at 2.68 t/s. Prefill runs at ~73 tok/s. Unpruned tiers are 883 GB and above and do not fit any Apple Silicon machine.