Hy3
1recorded run
27.6best tok/s
1verified
Fastest GPUs for this model (best tok/s)
- CMP 170HX x227.6
| GPU | Model | Quant | Backend | Ctx | tok/s | prompt tok/s | VRAM GB | Source |
|---|---|---|---|---|---|---|---|---|
| CMP 170HX x2 · 64 GB | Hy3 | Q2_K_XL | llama.cpp 0.28.0 | 32768 | 27.6 ✓ | 250.7 | 115.9 | src |
| GPU | Model | Quant | Backend | Ctx | tok/s | prompt tok/s | VRAM GB | Source |
|---|---|---|---|---|---|---|---|---|
| CMP 170HX x2 · 64 GB | Hy3 | Q2_K_XL | llama.cpp 0.28.0 | 32768 | 27.6 ✓ | 250.7 | 115.9 | src |