DeepSeek V4 Flash 0731, prepared complete 4K prefill
on AMD Strix Halo 128GB · DS4 Halo (October 6 candidate) · 4,352 ctx
Summary
User reports DeepSeek V4 Flash prefill at 454.6 t/s on an AMD Ryzen AI Max+ 395 / Radeon 8060S (gfx1151) with 128 GB unified memory.
Setup is the DS4 Halo ROCm prefill fork with IQ2_XXS + Q2_K and selected Q8 tensors, 4,352-token context allocation and 4,096-token prefill chunks.
The figure is a warmed prepared-prefill mean of 454.59 t/s from two samples, 454.52 and 454.65, on a complete position-zero 4,096-token request with generation disabled.