cfg-0101
citable URL: https://halobench.com/records/cfg-0101/ — this address never moves; the anchor /records/#cfg-0101 keeps resolving
| model | always42-universal.gguf · F16 · rev main |
| 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 |
Memory — static estimate vs observed peak
context 8,192 × 1 slot(s) = 8,192 tokens
⌁ total 1.15 GiB of 120 GiB pool · ⌁ headroom 118.85 GiB
⌁ risk utilisation 1.0% — basis observed
Capability basis
measured on this config
Runs on this config (6)
| run | date | kind | suite | metrics |
|---|---|---|---|---|
| run-0363 | 2026-08-17 | guard | deep-thought-posttrain-fullbench | tasks_passed=2 · tasks_total=4 |
| run-0364 | 2026-08-17 | performance | llama-bench@1 | prefill_tps=16740.778 |
| run-0365 | 2026-08-17 | performance | llama-bench@1 | decode_tps=187.53 |
| run-0366 | 2026-08-17 | performance | llama-bench@1 | prefill_tps=9276.909 |
| run-0367 | 2026-08-17 | performance | llama-bench@1 | decode_tps=164.871 |
| run-0372 | 2026-08-17 | capability | deep-thought-posttrain-fullbench | tasks_passed=5 · tasks_total=14 · mean_score=0.3571 |
Cited by — computed at build time, never stored
model pages deep-thought-posttrain