cfg-0104
backfilled
citable URL: https://halobench.com/records/cfg-0104/ — this address never moves; the anchor /records/#cfg-0104 keeps resolving
| model | Ornith-1.0-35B-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 |
| 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-0094 (identical llama-bench invocation: build 3653e6d, ROCm, Q8_0, f16 KV, -fa 1 — the `flags` text matches cfg-0094 verbatim so the site's chart series can merge them; --load-mode none was passed on the actual command line, same as cfg-0094's own invocation, it is simply not part of either config's recorded flags string — only depth differs between the two configs' actual runs, not a fingerprint field). A fresh config id is minted per house convention (each backfill invocation gets its own config record). 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-0377 | 2026-08-17 | performance | llama-bench@1 | prefill_tps=173.658178 |
| run-0378 | 2026-08-17 | performance | llama-bench@1 | decode_tps=22.232903 |
| run-0379 | 2026-08-17 | performance | llama-bench@1 | prefill_tps=141.960239 |
| run-0380 | 2026-08-17 | performance | llama-bench@1 | decode_tps=19.36695 |
Cited by — computed at build time, never stored
model pages ornith-35b