Gemma 4 DiffusionGemma-26B-A4B-it
on AMD Ryzen AI Max+ 395 / Radeon 8060S (Strix Halo; 121 GiB unified memory reported) · Gufo · 131,072 ctx
Summary
User reports Gemma 4 at 3116 t/s prompt processing on one AMD Ryzen AI Max+ 395 / Radeon 8060S integrated GPU (Strix Halo).
Setup is the Gufo native HIP engine with FP8 safetensors and a configured context of 131072, one request at a time.
The 3116 t/s is native prefill for a 2,261-input-token book prompt with 512 output tokens; the same sweep drops to 1329 t/s at 121,294 input tokens.