cfg-0008
backfilled
citable URL: https://halobench.com/records/cfg-0008/ — this address never moves; the anchor /records/#cfg-0008 keeps resolving
| model | Qwen3.5-122B-A10B-UD-Q4_K_M-00001-of-00003.gguf · UD-Q4_K_M |
| engine | ggml-org/llama.cpp 3653e6d · rocm · host aihydra (igpu) |
| flags | -ngl 999 -fa 0 -b 2048 -ub 512 -ctk f16 -ctv f16 -t 16 |
| template | not recorded at test time |
| tree | upstream — 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)
| run | date | kind | suite | metrics |
|---|---|---|---|---|
| run-0008 | 2026-08-08 | performance | llama-bench@1 | prefill_tps=312.037487 |
| run-0009 | 2026-08-08 | performance | llama-bench@1 | decode_tps=21.676081 |
| run-0010 | 2026-08-08 | performance | llama-bench@1 | prefill_tps=283.473901 |
| run-0011 | 2026-08-08 | performance | llama-bench@1 | decode_tps=19.258807 |
| run-0012 | 2026-08-08 | performance | llama-bench@1 | prefill_tps=170.811067 |
| run-0013 | 2026-08-08 | performance | llama-bench@1 | decode_tps=9.867545 |
Cited by — computed at build time, never stored
docs overnight-2026-08-08