cfg-0080
citable URL: https://halobench.com/records/cfg-0080/ — this address never moves; the anchor /records/#cfg-0080 keeps resolving
| model | Qwen3.8-27B-Q8_0.gguf · Q8_0 |
| engine | ggml-org/llama.cpp 3653e6d · vulkan · host aihydra (igpu) |
| flags | -ngl 999 -fa on -c 32768 -dev Vulkan0 --load-mode none --parallel 1 --slots --spec-type draft-mtp --spec-draft-n-max 5 --spec-draft-p-min 0.9 |
| template | not recorded at test time |
| tree | upstream — stock |
Capability basis
unmeasured — performance numbers on this config stand on a guard alone, not an established capability
Runs on this config (1)
| run | date | kind | suite | metrics |
|---|---|---|---|---|
| run-0284 | 2026-08-15 | guard | eos-cliff-isolation@1 | tasks_passed=14 · tasks_total=15 |