Home › Evidence › Records › cfg-0012

cfg-0012

backfilled
citable URL: https://halobench.com/records/cfg-0012/ — this address never moves; the anchor /records/#cfg-0012 keeps resolving
modelQwen3.6-35B-A3B-UD-Q4_K_XL.gguf · UD-Q4_K_XL
engineggml-org/llama.cpp 3653e6d · rocm · host aihydra (igpu)
flags-ngl 999 -fa 1 -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-00302026-08-08performancellama-bench@1prefill_tps=1079.379298
run-00312026-08-08performancellama-bench@1decode_tps=51.014596
run-00322026-08-08performancellama-bench@1prefill_tps=965.372738
run-00332026-08-08performancellama-bench@1decode_tps=49.804365
run-00342026-08-08performancellama-bench@1prefill_tps=598.677694
run-00352026-08-08performancellama-bench@1decode_tps=42.447348

Cited by — computed at build time, never stored

model pages qwen36-35b