Qwen 2.5 32B
2 records across 1 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2x RTX 5060 Ti | Qwen 2.5 32B | Q4_K_M | llama.cpp (CUDA) | 14.3 | – | – | – | 8192 | 2026-03-31 | community | – | source |
| 2x RTX 5060 Ti | Qwen 2.5 32B | Q4_K_M | llama.cpp (CUDA) | 5.5 | – | – | – | 8192 | 2026-03-31 | community | – | source |