llamaperf

DeepSeek V4 Flash 284B (13B active)

on M3 Ultra · MLX

Tone: positive
Sep 7, 2026
Throughput
43.0 t/s gen
Quant
MXFP4
System RAM
192 GB

Summary

User reports 34 t/s at the start of a run, rising to 43 t/s by the end. The cached tokens were the default chat prompt and the query was 13k.