Ornith 1.0-35B / Vulkan RADV native PP512/TG128
on AMD Strix Halo 128GB · llama.cpp / Vulkan RADV / build unknown
Summary
User reports Ornith-1.0-35B at 53.2 t/s generation and 1027 t/s prompt processing on an AMD Strix Halo 128GB system with a single Radeon 8060S iGPU.
Setup is llama.cpp via RADV with Q8_0, full offload, batch 2048 and flash attention.
The figures are separate 512-token prompt and 128-token generation microbenchmarks, not one end-to-end request; the AMDVLK arm reached 725.0 t/s prompt and 52.5 t/s generation.