7680 input

on AMD Ryzen AI MAX+ 395 / Radeon 8060S (Strix Halo gfx1151), 128 GB unified memory · llama.cpp

Oct 13, 2026

Throughput

17.3 t/s gen · 254.3 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.

Quant

UD-IQ3_XXS (GGUF)

KV cache

Flash Attention

System RAM

128 GB

Summary

User reports DeepSeek V4 Flash at 17.3 t/s generation and 254.3 t/s prompt processing on an AMD Ryzen AI MAX+ 395 with Radeon 8060S and 128 GB unified memory. Setup is llama.cpp (Nathanw1014/strix-halo-llamacpp v0.7.5, Vulkan backend) with UD-IQ3_XXS, K/V q8_0, flash attention, and no speculative decoding, on one Strix Halo GPU. The headline figures are the 7,680-input point of a three-point curve; at 30,720 input the rates are 247.7/17.4 and at 122,879 input 194.8/15.8 t/s.