Home › Evidence › Records › cfg-0004

cfg-0004

backfilled
citable URL: https://halobench.com/records/cfg-0004/ — this address never moves; the anchor /records/#cfg-0004 keeps resolving
modelnvidia/Nemotron-3-Super-GGUF · IQ4_XS
engineggml-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)
templatenot recorded at test time
treeupstream — 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