verifiedmedium · 0.75updated 2026-10-14

Strix Halo 8060S (Vulkan AMDVLK) Llama 2 7B Q4_0: pp512 prefill tok/s

1294.1 tok/s (pp512, per-request batch-1)

Fields

benchmarks/strix-halo-8060s-llama2-7b-q4-0-amdvlk-pp512

Metric

prefill_tok_s

Value

1,294.1

Unit

tok/s (pp512, per-request batch-1)

Model

Llama 2 7B

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 4281 MiB. Numbers verbatim from the best-backend summary table.

Measured by

third_party

Reproducible

yes

Cross-references

Strix Halo 8060S (Vulkan AMDVLK) Llama 2 7B Q4_0: pp512 prefill tok/s

Fields

Cross-references

Accelerators (2)

Engine (1)

Interconnect (1)