inference/research
verifiedmedium · 0.70updated 2026-10-15

kyuz0 Strix Halo 8060S GLM-4.7-Flash-UD-Q8_K_XL ROCm 7.2.3 pp512

913.36 tok/s

Fields

id
benchmarks/kyuz0-8060s-glm-47-flash-ud-q8-k-xl-rocm-723-pp512
Metric
prefill_tok_s
Value
913.36
Unit
tok/s
Model
GLM-4.7-Flash-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). ROCm 7.2.3, -fa 1 -ngl 99 --mmap 0, default ctx. pp512 batch-1 per-request.
Measured by
third_party
Reproducible
yes

Cross-references