cfg-0174
backfilledfork
citable URL: https://halobench.com/records/cfg-0174/ — this address never moves; the anchor /records/#cfg-0174 keeps resolving
| model | Qwen3.8-27B-ROCMFPX-MQ-Q4.gguf + Qwen3.8-27B-DFlash2-Q8_0.gguf · ROCmFPX-MQ-Q4 + DFlash2-Q8_0 |
| engine | LaurentZuijdwijk/llama.cpp 16f0799a6 · Vulkan0/RADV Mesa 26.0.3 · host aihydra (igpu) |
| flags | Operator-directed autonomous tuning served-path screen: target ROCmFPX-MQ-Q4 with DFlash2 Q8_0 drafter, -dev Vulkan0 -ngl 99 -c 32768 -fa on -t 16 -np 1 --jinja --spec-type draft-dflash --spec-draft-n-max 7 -ngld 99. The separate competence smoke used native MTP n_max 4 with reasoning medium, temperature 0.1, max_tokens 8192, tasks 0-4, seed 42, and the pinned Haiku simulator. |
| template | not recorded at test time |
| tree | fork — carrying con-0013 |
aged evidence — reconstructed from the archive. The archived handoff does not provide target/drafter SHA256s, a chat-template hash, a standard house-guard artifact, a plain/spec-off paired served-path floor, or a llama-bench floor. The server samples are retained as screening evidence, not a production-performance or quant-equivalence admission.
Capability basis
unmeasured — performance numbers on this config stand on a guard alone, not an established capability
Runs on this config (3)
| run | date | kind | suite | metrics |
|---|---|---|---|---|
| run-0626 | 2026-08-24 | performance | qwen38-prod-tuning.server-screen-code@1 | decode_tps=52.2 |
| run-0627 | 2026-08-24 | capability | tau2-airline-smoke@tasks-0-4 | tasks_passed=5 · tasks_total=5 · mean_score=1 |
| run-0631 | 2026-08-24 | performance | qwen38-prod-tuning.server-screen-prose@1 | decode_tps=31.5 |
Cited by — computed at build time, never stored
claims clm-0120