granite-4.2-30b
Llama family · 29.0B params
1recorded run
23.7best tok/s
1verified
Fastest GPUs for this model (best tok/s)
- CMP 170HX23.7
All benchmarks Methodology
| GPU | Model | Quant | Backend | Ctx |
tok/s | prompt tok/s | VRAM GB | Source |
| CMP 170HX · 64 GB | granite-4.2-30b | Q8_0 | llama.cpp 0.3.0-dev+b10705 | 65797 | 23.7 ✓ | 624.0 | — | src |