llamaperf

DeepSeek V4 Flash 284B (13B active)

on NVIDIA DGX Spark · 256,000 ctx

Tone: positiveNVIDIA hardware
Sep 7, 2026
Throughput
40.0 t/s gen
Quant
FP8

Summary

User reports DeepSeek V4 Flash at about 40 t/s single-stream and 350 t/s aggregate with 32 concurrent requests at 256k context on dual DGX Sparks. The 350 t/s figure is an aggregate across the 32 concurrent requests. User compares this to an RTX Pro 6000 at about 46 t/s and a Mac M2 Ultra 192GB at about 29 t/s, both at Q2.