cfg-0164
backfilledfork
citable URL: https://halobench.com/records/cfg-0164/ — this address never moves; the anchor /records/#cfg-0164 keeps resolving
| model | Qwen3.8-27B-IU4-Kairic-Edge.gguf · IU4 · rev 360caf7381907c3eca7ac0afd1228efc016af747f3f38637fb1c7f94daabac2a |
| engine | ciru-ai/ROCmFPX e1da26bb8 · rocm · host aihydra (igpu) |
| flags | The Kairic Edge TheRock served config at c32768 on this build (compat mode; prompts even fast-greedy forbids tool calls) used by HK-001-FULLBENCH. Generic flag set (per the fullbench launch script): -m Qwen3.8-27B-IU4-Kairic-Edge.gguf -dev ROCm0 -ngl 999 -c 32768 -b 2048 -ub 512 -fa on -ctk f16 -ctv f16 -t 16 -tb 32 -np 1 --no-mmap --kairic-edge --metrics -n 4096 --slots with the PROMPTFORGE_* env block (PROMPTFORGE_MODE=iu4_ffn, IU4/GDN/GDN-Output sidecar pfs paths, HADAMARD+SEGMENTED switches). PLAIN spec only — NO MTP (n_max>=4 cliff on the Qwen3.8 family, clm-0055). --kairic-edge and the sidecars are server-only; llama-bench (the engine path that produced the depth-ladder cells) can NOT carry the flag or the GDN row, so the depth cells are recorded as engine-path on this same build+sidecar-env, per protocol 1d. |
| template | not recorded at test time |
| tree | fork — carrying con-0012 |
aged evidence — reconstructed from the archive. Fingerprint reconstructed from the HK-001-FULLBENCH launch script and build doc (hk001-results-r1.md + scratch/hk001-launch.sh) — exact start_server invocation not re-verified on-box (the runner's logs are on aihydra, build commit e1da26bb8 / binary e121a4d3; model sha 360caf73; sidecar hashes adcbb90a / 82f93131 / 3b07e7b1). Capability is measured (guard exercised 3/3 + isolation N/A), everything on the launched served config; the throughput/depth cells are engine-path (llama-bench). Single config record for this build; every HK-001-FULLBENCH run below points at it.
Capability basis
measured on this config
Runs on this config (4)
| run | date | kind | suite | metrics |
|---|---|---|---|---|
| run-0601 | 2026-08-23 | guard | hk001-fullbench-guard@c32768 | tasks_passed=3 · tasks_total=3 |
| run-0602 | 2026-08-23 | performance | hk001-fullbench-fit@c32768 | decode_tps=11.73 · prefill_tps=279.6 |
| run-0603 | 2026-08-23 | performance | hk001-fullbench-depth-r3@llama-bench | decode_tps=13.14 · prefill_tps=612.3 |
| run-0604 | 2026-08-23 | performance | hk001-fullbench-depth-r3@llama-bench | decode_tps=11.66 · prefill_tps=272.1 |
Cited by — computed at build time, never stored
claims clm-0116