cfg-0016
backfilled
citable URL: https://halobench.com/records/cfg-0016/ — this address never moves; the anchor /records/#cfg-0016 keeps resolving
| model | gpt-oss-120b-UD-Q4_K_XL-00001-of-00002.gguf · UD-Q4_K_XL |
| engine | ggml-org/llama.cpp 3653e6d · rocm · host aihydra (igpu) |
| flags | -ngl 999 -fa 1 -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-0044 | 2026-08-08 | performance | llama-bench@1 | prefill_tps=450.832446 |
| run-0045 | 2026-08-08 | performance | llama-bench@1 | decode_tps=55.454588 |
| run-0046 | 2026-08-08 | performance | llama-bench@1 | prefill_tps=421.546647 |
| run-0047 | 2026-08-08 | performance | llama-bench@1 | decode_tps=52.793591 |
| run-0048 | 2026-08-08 | performance | llama-bench@1 | prefill_tps=308.546401 |
| run-0049 | 2026-08-08 | performance | llama-bench@1 | decode_tps=41.698106 |
Cited by — computed at build time, never stored
model pages gpt-oss-120b