cfg-0103
backfilled
citable URL: https://halobench.com/records/cfg-0103/ — this address never moves; the anchor /records/#cfg-0103 keeps resolving
| model | Qwen3.8-27B-Q8_0.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 --load-mode none |
| template | not recorded at test time |
| tree | upstream — stock |
aged evidence — reconstructed from the archive. Depth-ladder backfill session (2026-08-17), same fingerprint as cfg-0062 (identical llama-bench invocation: build 3653e6d, ROCm, Q8_0, f16 KV, -fa 1, --load-mode none — only depth differs, which is not a fingerprint field). A fresh config id is minted per house convention (each backfill invocation gets its own config record rather than silently appending to a prior session's), matching the qwen36-27b-mtp d204800 backfill precedent (cfg-0100 vs its own cfg-0097). Ingested from llama-bench, which measures throughput and not footprint: the memory block, chat-template hash and model revision are absent by construction. Everything present here — build commit, backend, KV quant, batch sizes, flash attention, load-mode — is machine-reported at launch.
Capability basis
unmeasured — performance numbers on this config stand on a guard alone, not an established capability
Runs on this config (4)
| run | date | kind | suite | metrics |
|---|---|---|---|---|
| run-0373 | 2026-08-17 | performance | llama-bench@1 | prefill_tps=61.002739 |
| run-0374 | 2026-08-17 | performance | llama-bench@1 | decode_tps=5.449447 |
| run-0375 | 2026-08-17 | performance | llama-bench@1 | prefill_tps=51.225787 |
| run-0376 | 2026-08-17 | performance | llama-bench@1 | decode_tps=5.025283 |
Cited by — computed at build time, never stored
model pages qwen38-27b