cfg-0151
citable URL: https://halobench.com/records/cfg-0151/ — this address never moves; the anchor /records/#cfg-0151 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 production-optimisation matrix Cell-1 baseline (b2048/ub512, q8_0/q8_0 KV) + Cell-2 depth probe fingerprint. llama-server build ce7689f (llama.cpp-kvfix tree), -ngl 999 -fa 1 -c 32768 --parallel 1 --load-mode none --jinja -rea off -ctk q8_0 -ctv q8_0 -b 2048 -ub 512 -t 16 -n 4096, ROCm0 Radeon 8060S gfx1151 122880 MiB. Cell-2 depth via llama-bench -p 16384 -n 256 -d 262144 -r 1 on the same b2048/ub512 q8_0/q8_0 signature. From per-execution command files (server-c1-b2048-ub512.command.txt and cell2-depth/c2-d262144.command.txt). |
| 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 (3)
| run | date | kind | suite | metrics |
|---|---|---|---|---|
| run-0579 | 2026-08-23 | performance | ho012-122b-prod-matrix-r2.cell1 | decode_tps=21.8436 · ttft_ms=1420.66 |
| run-0585 | 2026-08-23 | performance | ho012-122b-prod-matrix-r2.cell2-depth | decode_tps=8.447554 · prefill_tps=62.2502 |
| run-0588 | 2026-08-23 | guard | guard-c32768-depth8000 | tasks_passed=4 · tasks_total=4 |
Cited by — computed at build time, never stored
claims clm-0111