Baguettotron 321M / BF16 / Vulkan native PP512 TG128 / runtime build unknown
on AMD Strix Halo 128GB · llama.cpp / Vulkan KHR cooperative matrices / build unknown
Summary
User reports Baguettotron 321M at 185 t/s generation and 5879 t/s prompt processing on an AMD Strix Halo 128GB machine.
Setup is llama.cpp with Vulkan on the Radeon 8060S iGPU, BF16 weights, 6 threads, and -ngl 999 for maximum GPU offload.
The figures come from separate llama-bench phase tests, PP512 and TG128, not an end-to-end rate; the rates are rounded and no raw timings, context depth, or KV cache details are reported.