cfg-0106
backfilled
citable URL: https://halobench.com/records/cfg-0106/ — this address never moves; the anchor /records/#cfg-0106 keeps resolving
| model | Ornith-1.0-35B-Q8_0.gguf · Q8_0 |
| engine | ggml-org/llama.cpp 3653e6d6d · vulkan · 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. Part 2 deep-cell session (2026-08-17), same fingerprint as cfg-0105 (identical llama-bench invocation: build 3653e6d6d, Vulkan, Q8_0, f16 KV, -fa 1, --load-mode none -- only depth differs, which is not a fingerprint field). This is the model-max cell (d262144) that extends cfg-0105's d204800 Vulkan-survival streak to ornith-35b's declared context ceiling. A fresh config id is minted per house convention. Ingested from llama-bench, which measures throughput and not footprint.
Capability basis
unmeasured — performance numbers on this config stand on a guard alone, not an established capability
Runs on this config (2)
| run | date | kind | suite | metrics |
|---|---|---|---|---|
| run-0383 | 2026-08-17 | performance | llama-bench@1 | prefill_tps=84.244716 |
| run-0384 | 2026-08-17 | performance | llama-bench@1 | decode_tps=23.305531 |
Cited by — computed at build time, never stored
model pages ornith-35b