OpenLLaMA-3B
LLaMA family · 3.0B params
1recorded run
2.4best tok/s
1verified
Fastest GPUs for this model (best tok/s)
- GT 4302.4
All benchmarks Methodology
| GPU | Model | Quant | Backend | Ctx |
tok/s | prompt tok/s | VRAM GB | Source |
| GT 430 | OpenLLaMA-3B | Q4_0 | llama.cpp 2e6cd4b | 512 | 2.4 ✓ | — | — | src |