kyuz0 Strix Halo 8060S Qwen3.6-35B-A3B-UD-Q8_K_XL Vulkan AMDVLK tg128
46.53 tok/s
Fields
id
benchmarks/kyuz0-8060s-qwen36-35b-a3b-ud-q8-k-xl-vulkanamdvlk-tg128Metric
decode_tok_s
Value
46.53
Unit
tok/s
Model
Qwen3.6-35B-A3B-UD-Q8_K_XL
Methodology
kyuz0 amd-strix-halo-toolboxes llama-bench sweep (results.json 2026-05-16, Fedora 43 kernel 6.19.12, llama.cpp b9187/9193). Vulkan AMDVLK, -fa 1 -ngl 99 --mmap 0, default ctx. tg128 batch-1 per-request.
Measured by
third_party
Reproducible
yes