cfg-0132
backfilled
citable URL: https://halobench.com/records/cfg-0132/ — this address never moves; the anchor /records/#cfg-0132 keeps resolving
| model | Qwen3.6-35B-A3B-MTP-UD-Q4_K_M.gguf · UD-Q4_K_M · rev 0b21525e972670ed59e1812e170b27c26355381f0656ecc4e25617ece7dac58b |
| engine | ggml-org/llama.cpp 7077abbe14c510cb829c93a1328c2815b5805ebd · ROCm0/gfx1151 · host aihydra (igpu) |
| flags | HO-009 plain/control fingerprint: /home/aihydra/src/llama.cpp-master-bailingmoe3, server build 50 commit 7077abb, ROCm0 Radeon 8060S, --load-mode none, -ngl 999, flash attention on, -b 2048, -ub 512, f16/f16 KV, --parallel 1, no proxy/llama-swap/ngram/external drafter/speculation. |
| template | not recorded at test time |
| tree | upstream — stock |
aged evidence — reconstructed from the archive. Reviewer-admitted HO-009 plain baseline for the genuine Qwen3.6-35B-A3B-MTP UD-Q4_K_M artifact at /home/aihydra/bench-results/ho009-qwen36-35b-a3b-mtp-refinement-r2. This is an activation/safety/performance boundary only, not a capability or production claim.
Capability basis
measured on this config
Runs on this config (7)
| run | date | kind | suite | metrics |
|---|---|---|---|---|
| run-0524 | 2026-08-20 | performance | stageA-c32768 | decode_tps=51.567783 |
| run-0528 | 2026-08-20 | guard | guard-c32768-depth8000 | tasks_passed=4 · tasks_total=4 |
| run-0530 | 2026-08-20 | performance | llama-bench@1 | decode_tps=52.429453 · prefill_tps=1061.377092 |
| run-0531 | 2026-08-20 | performance | llama-bench@1 | decode_tps=43.107742 · prefill_tps=600.282617 |
| run-0532 | 2026-08-20 | performance | llama-bench@1 | decode_tps=28.783536 · prefill_tps=251.893544 |
| run-0533 | 2026-08-20 | performance | llama-bench@1 | decode_tps=22.986826 · prefill_tps=175.137524 |
| run-0534 | 2026-08-20 | performance | llama-bench@1 | decode_tps=19.970905 · prefill_tps=143.241994 |