| 量子化 | Size | OS | CPU | RAM | RAM | GPU | Window | token/s | software | |
|---|---|---|---|---|---|---|---|---|---|---|
| UD_Q4_K_XL | 77 GB | Ubuntu 24.04 | Ryzen 9 3950X (65W) | DDR4-3200 | 128GB | GeForce RTX 4060Ti 16GB | 4096 | 8.3 tps | llama.cpp b8319 | |
| Q4_K_M | 80 GB | Windows11 | Ryzen 7 9700X | DDR5-5600 | 128GB | GeForce RTX 5060Ti 16GB | 4096 | 10.98 tps | LMStudio 0.4.6 CUDA 12 v2.7.0 |