OpenReasoning-Nemotron-7B
1recorded run
68.0best tok/s
1verified
Fastest GPUs for this model (best tok/s)
- RTX 3060 x268.0
| GPU | Model | Quant | Backend | Ctx | tok/s | prompt tok/s | VRAM GB | Source |
|---|---|---|---|---|---|---|---|---|
| RTX 3060 x2 · 12 GB | OpenReasoning-Nemotron-7B | Q4_K_M | llama.cpp 13f2b28 | 512 | 68.0 ✓ | 2264.1 | 7.3 | src |