DeepSeek V4 Flash / layers37-42 Q4 experts hybrid / ds4 2K frontier, full32-point curve
on AMD Radeon 8060S integrated GPU (Strix Halo) · ds4 (ROCm 7.2.4) · 65,665 ctx
Summary
User reports DeepSeek V4 at 15 t/s generation and 138 t/s prefill on an AMD Radeon 8060S. Setup is ds4-bench on ROCm 7.2.4 with a Q4K/IQ2XXS hybrid quant and a 65665-token context allocation. The figures come from the first 2048-token frontier of a 32-point sweep to 65536, with 2048 prefill and 128 generation tokens per row; generation falls to 12.17 t/s at the deepest frontier.