cfg-0112
backfilled
citable URL: https://halobench.com/records/cfg-0112/ — this address never moves; the anchor /records/#cfg-0112 keeps resolving
| model | Qwen3-Coder-Next-Q8_0-00001-of-00004.gguf · Q8_0 |
| 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 (18)
| run | date | kind | suite | metrics |
|---|---|---|---|---|
| run-0396 | 2026-08-17 | performance | llama-bench@1 | prefill_tps=479.242014 |
| run-0397 | 2026-08-17 | performance | llama-bench@1 | decode_tps=37.589295 |
| run-0398 | 2026-08-17 | performance | llama-bench@1 | prefill_tps=457.804703 |
| run-0399 | 2026-08-17 | performance | llama-bench@1 | decode_tps=37.650766 |
| run-0400 | 2026-08-17 | performance | llama-bench@1 | prefill_tps=492.747337 |
| run-0401 | 2026-08-17 | performance | llama-bench@1 | decode_tps=37.732493 |
| run-0402 | 2026-08-17 | performance | llama-bench@1 | prefill_tps=174.127892 |
| run-0403 | 2026-08-17 | performance | llama-bench@1 | decode_tps=21.285063 |
| run-0404 | 2026-08-17 | performance | llama-bench@1 | prefill_tps=124.602502 |
| run-0405 | 2026-08-17 | performance | llama-bench@1 | decode_tps=17.509175 |
| run-0406 | 2026-08-17 | performance | llama-bench@1 | prefill_tps=104.559456 |
| run-0407 | 2026-08-17 | performance | llama-bench@1 | decode_tps=15.464558 |
| run-0408 | 2026-08-17 | performance | llama-bench@1 | prefill_tps=348.26267 |
| run-0409 | 2026-08-17 | performance | llama-bench@1 | decode_tps=30.426219 |
| run-0410 | 2026-08-17 | performance | llama-bench@1 | prefill_tps=343.855736 |
| run-0411 | 2026-08-17 | performance | llama-bench@1 | decode_tps=31.836263 |
| run-0412 | 2026-08-17 | performance | llama-bench@1 | prefill_tps=348.32493 |
| run-0413 | 2026-08-17 | performance | llama-bench@1 | decode_tps=30.905586 |
Cited by — computed at build time, never stored
model pages qwen3-coder-next-80b