cfg-0028
backfilled
citable URL: https://halobench.com/records/cfg-0028/ — this address never moves; the anchor /records/#cfg-0028 keeps resolving
| model | NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-00001-of-00003.gguf · UD-Q4_K_M |
| engine | ggml-org/llama.cpp 3653e6d6d547ec763317d9ecd0ace334a7e21359 · rocm · host aihydra (igpu) |
| flags | -ngl 999 -fa on -c 32768 --parallel 1 --load-mode none --jinja -rea off -ctk f16 -ctv f16 |
| template | not recorded at test time |
| tree | upstream — stock |
aged evidence — reconstructed from the archive. cfg-0027 with the model at UD-Q4_K_M — Stage E1 of the quant-pair deconfound (clm-0047): the two arms differ only in the model file's quantisation. Flags from bench/queues/queue-e-nemotron-quant.sh; build asserted at launch. Same gaps as cfg-0027.
Capability basis
measured on this config
Runs on this config (1)
| run | date | kind | suite | metrics |
|---|---|---|---|---|
| run-0107 | 2026-08-11 | capability | tau2-bench-airline@668d3bc | tasks_passed=7 · tasks_total=12 · mean_score=0.5833 |