cp: warning: behavior of -n is non-portable and may change in future; use --update=none instead
3
=== Rohlesetest (direkt, 8 GiB, ohne Cache) ===
/mnt/models/models/gguf/Swift-IQ3_XXS/Swift-Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-00002-of-00002.gguf
8589934592 bytes (8.6 GB, 8.0 GiB) copied, 1.97316 s, 4.4 GB/s
/home/qni/models-gguf/Swift-IQ3_XXS/Swift-Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-00002-of-00002.gguf
8589934592 bytes (8.6 GB, 8.0 GiB) copied, 1.22488 s, 7.0 GB/s
evicted 58
Speicher:         61           3          57           0           0          57
START mnt lauf1: 24.482974565 s bis erste Antwort
[strata] experts loaded: 39.97 GiB at 6.40 GiB/s (19 s so far)
[strata] filling the GPU's expert cache (12800 experts, 18.62 GiB of VRAM) ...
[strata] almost ready ...
evicted 58
Speicher:         61           3          57           0           0          57
START gen5 lauf1: 23.893165572 s bis erste Antwort
[strata] experts loaded: 39.97 GiB at 6.36 GiB/s (20 s so far)
[strata] filling the GPU's expert cache (12800 experts, 18.62 GiB of VRAM) ...
[strata] almost ready ...
evicted 58
Speicher:         61           3          57           0           0          57
START mnt lauf2: 23.926122935 s bis erste Antwort
[strata] experts loaded: 39.97 GiB at 6.41 GiB/s (20 s so far)
[strata] filling the GPU's expert cache (12800 experts, 18.62 GiB of VRAM) ...
[strata] almost ready ...
evicted 58
Speicher:         61           3          57           0           0          57
START gen5 lauf2: 23.910973191 s bis erste Antwort
[strata] experts loaded: 39.97 GiB at 6.34 GiB/s (20 s so far)
[strata] filling the GPU's expert cache (12800 experts, 18.62 GiB of VRAM) ...
[strata] almost ready ...
=== FERTIG, Dienst laeuft zuletzt auf gen5 ===
