gpt-oss 21B (3.6B active)
on AMD Strix Halo 128GB · llama.cpp / Vulkan KHR cooperative matrices / build unknown
Summary
User reports gpt-oss 20B at 77 t/s generation and 1216 t/s prompt processing on an AMD Strix Halo 128GB machine.
Setup is llama.cpp Vulkan on the Radeon 8060S iGPU with MXFP4 quantization, 6 threads and maximum GPU offload (ngl 999).
The figures come from separate llama-bench phase tests, PP512 and TG128, not an end-to-end rate; rates are rounded and context depth, KV precision and batch settings are unreported.