cfg-0158
backfilled
citable URL: https://halobench.com/records/cfg-0158/ — this address never moves; the anchor /records/#cfg-0158 keeps resolving
| model | Qwen3.5-122B-A10B-UD-Q4_K_M-00001-of-00003.gguf · UD-Q4_K_M |
| engine | ggml-org/llama.cpp ce7689f · ROCm0/gfx1151 · host aihydra (igpu) |
| flags | HO-012 Cell-3 KV q4_0 arm:llama-server build ce7689f (llama.cpp-kvfix), -ngl 999 -fa 1 -c 32768 --parallel 1 --load-mode none --jinja -rea off -ctk q4_0 -ctv q4_0 -b 2048 -ub 512 -t 16 -n 4096, ROCm0 Radeon 8060S gfx1151 122880 MiB. Identical to cfg-0151 EXCEPT -ctk q4_0 -ctv q4_0 (KV quant lever). From server-c3-q4_0.command.txt. |
| template | not recorded at test time |
| tree | upstream — stock |
aged evidence — reconstructed from the archive. From reviewer-admitted HO-012 evidence. kv_quant is a LOSSY capability lever, so capability is NOT inherited; this arm is a throughput/delta cell only, guarded 4/4, no capability claim. q4_0/q4_0 KV, b2048/ub512. Intra-suite only; the q4_0 decode regression vs f16 is recorded truthfully (see clm-0111), never as equivalence.
Capability basis
unmeasured — performance numbers on this config stand on a guard alone, not an established capability
Runs on this config (2)
| run | date | kind | suite | metrics |
|---|---|---|---|---|
| run-0587 | 2026-08-23 | performance | ho012-122b-prod-matrix-r2.cell3-q4_0 | decode_tps=21.8276 · ttft_ms=1418.99 |
| run-0590 | 2026-08-23 | guard | guard-c32768-depth8000 | tasks_passed=4 · tasks_total=4 |
Cited by — computed at build time, never stored
claims clm-0111