basic-benchmark/llama-server-1-headless.txt
smill 0cd63d0233 basic-benchmark: portable Fedora benchmark kit
Headless + headed suites with power/thermal logging and efficiency reporting.
Includes PassMark, llama.cpp, app workloads (LibreOffice/GEGL/Inkscape/GIMP),
a GOVERNOR selector, compare-report.py, and captured results.
2026-09-29 21:06:24 -04:00

7 lines
628 B
Text

ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = Intel(R) Iris(R) Plus Graphics (ICL GT2) (Intel open-source Mesa driver) | uma: 1 | fp16: 1 | bf16: 0 | fp4: 0 | warp size: 32 | shared memory: 49152 | int dot: 0 | matrix cores: none
| model | size | params | backend | ngl | test | t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | --------------: | -------------------: |
| llama ?B Q8_0 | 2.49 GiB | 2.52 B | Vulkan | 0 | tg128 | 13.29 ± 0.08 |
build: ce8caa6e6 (11065)