Strix Halo 8060S (Vulkan AMDVLK) Hunyuan-A13B UD-Q6_K_XL: pp512 prefill tok/s
296.6 tok/s (pp512, per-request batch-1)
Fields
id
benchmarks/strix-halo-8060s-hunyuan-a13b-udq6-amdvlk-pp512Metric
prefill_tok_s
Value
296.6
Unit
tok/s (pp512, per-request batch-1)
Model
Hunyuan-A13B
Methodology
THIRD-PARTY MEASURED (lhl/strix-halo-testing llm-bench summary table). Hardware: Framework Desktop, AMD Ryzen AI Max+ 395 (Strix Halo) + Radeon 8060S iGPU, 128GB LPDDR5x-8000 unified memory. llama.cpp ~b5863, Vulkan AMDVLK backend, flags fa=1; llama-bench -fa 1 --mmap 0 -ngl 99, pp512 + tg128, per-request batch-1. Peak resident 69179 MiB. Numbers verbatim from the best-backend summary table.
Measured by
third_party
Reproducible
yes