Home › Evidence › Records › cfg-0008

cfg-0008

backfilled
citable URL: https://halobench.com/records/cfg-0008/ — this address never moves; the anchor /records/#cfg-0008 keeps resolving
modelQwen3.5-122B-A10B-UD-Q4_K_M-00001-of-00003.gguf · UD-Q4_K_M
engineggml-org/llama.cpp 3653e6d · rocm · host aihydra (igpu)
flags-ngl 999 -fa 0 -b 2048 -ub 512 -ctk f16 -ctv f16 -t 16
templatenot recorded at test time
treeupstream — stock
aged evidence — reconstructed from the archive. Ingested from llama-bench, which measures throughput and not footprint: the memory block, chat-template hash and model revision are absent by construction. Peak memory comes from a Tier 0 capability probe, not from this tool. Everything present here — build commit, backend, KV quant, batch sizes, flash attention — is machine-reported.

Capability basis

unmeasured — performance numbers on this config stand on a guard alone, not an established capability

Runs on this config (6)

rundatekindsuitemetrics
run-00082026-08-08performancellama-bench@1prefill_tps=312.037487
run-00092026-08-08performancellama-bench@1decode_tps=21.676081
run-00102026-08-08performancellama-bench@1prefill_tps=283.473901
run-00112026-08-08performancellama-bench@1decode_tps=19.258807
run-00122026-08-08performancellama-bench@1prefill_tps=170.811067
run-00132026-08-08performancellama-bench@1decode_tps=9.867545

Cited by — computed at build time, never stored