cfg-0004
backfilled
citable URL: https://halobench.com/records/cfg-0004/ — this address never moves; the anchor /records/#cfg-0004 keeps resolving
| model | nvidia/Nemotron-3-Super-GGUF · IQ4_XS |
| engine | ggml-org/llama.cpp unknown-2026-06 · rocm · host aibeast (igpu) |
| flags | -ngl 999 --no-mmap --parallel 1 -fa 1 --jinja -c 131072 (reasoning OFF / enable_thinking:false; q8_0 KV) |
| template | not recorded at test time |
| tree | upstream — stock |
aged evidence — reconstructed from the archive. llama.cpp commit, chat-template hash and the per-model memory block were not recorded at test time. Quant, backend, context, KV quant, serving flags and the reasoning setting are from the Phase 3C write-up.
Capability basis
unmeasured — performance numbers on this config stand on a guard alone, not an established capability
production node(s): nemotron3-super