rune-26b-a4b-v3
2 records across 1 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2× Quadro RTX 4000 | rune-26b-a4b-v3 | IQ3_S-dyn | llama.cpp (CUDA) | – | 2098 | – | – | 2048 | 2026-10-03 | community | – | source |
| 2× Quadro RTX 4000 | rune-26b-a4b-v3 | IQ3_S-dyn | llama.cpp (CUDA) | – | 1904 | – | – | 14478 | 2026-10-03 | community | – | source |