cfg-0063
backfilled
citable URL: https://halobench.com/records/cfg-0063/ — this address never moves; the anchor /records/#cfg-0063 keeps resolving
| model | Qwen3.8-27B-UD-Q4_K_XL.gguf · UD-Q4_K_XL |
| 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. Ingested from llama-bench, which measures throughput and not footprint: the memory block, chat-template hash and model revision are absent by construction. Peak memory comes from a Tier 0 capability probe, not from this tool. Everything present here — build commit, backend, KV quant, batch sizes, flash attention — is machine-reported at launch. --load-mode none comes from the queue invocation itself (bench/queue-qwen38-screen.sh passes -lm none on every rep), added per clm-0053's rule that benchmark flags must match the serving standard on unified memory.
Capability basis
unmeasured — performance numbers on this config stand on a guard alone, not an established capability
Runs on this config (6)
| run | date | kind | suite | metrics |
|---|---|---|---|---|
| run-0251 | 2026-08-14 | performance | llama-bench@1 | prefill_tps=346.49 |
| run-0252 | 2026-08-14 | performance | llama-bench@1 | decode_tps=11.4415 |
| run-0253 | 2026-08-14 | performance | llama-bench@1 | prefill_tps=207.606 |
| run-0254 | 2026-08-14 | performance | llama-bench@1 | decode_tps=10.3626 |
| run-0255 | 2026-08-14 | performance | llama-bench@1 | prefill_tps=95.5937 |
| run-0256 | 2026-08-14 | performance | llama-bench@1 | decode_tps=8.13583 |
Cited by — computed at build time, never stored
model pages qwen38-27b