| Host: Intel(R) Xeon(R) Platinum 8559C | |
| Host threads: 192 | |
| Host MemTotal: 2147448086528 bytes (reported by /proc/meminfo) | |
| Container cgroup memory.max: 104000000000 bytes | |
| Container cgroup memory.swap.max: 2936848384 bytes | |
| Container cgroup memory.high: max | |
| GPU: unavailable; all tests ran on CPU | |
| Model file: Ling-3.0-tiny-Q4_K_M.gguf | |
| Model size: 4823894944 bytes | |
| Model source: inclusionAI/Ling-3.0-tiny-GGUF | |
| llama.cpp base commit: c811cb8f0ac91b8ac72a32f970bdd45037f20da7 | |
| Build: Release, GGML_NATIVE=OFF, GGML_CPU_REPACK=OFF, AVX512/VNNI enabled, AMX disabled | |
| Hard limit: prlimit --data (RLIMIT_DATA) | |
| Benchmark: ctx=256 ubatch=32 threads=4 temp=0 n_predict=32 repeats=2 | |
| Page cache: per-run posix_fadvise(POSIX_FADV_DONTNEED) | |