Multi-GPU x2
2recorded runs
160.9best tok/s
0sourced
How it compares — 24 GB per card · multi-GPU
All benchmarks Compare Multi-GPU x2 →
| GPU | Model | Quant | Backend | Ctx | tok/s | prompt tok/s | VRAM GB | Source |
|---|---|---|---|---|---|---|---|---|
| Multi-GPU x2 · 24 GB | Qwen3-8B | Q4_K_M | llama.cpp — | 2048 | 160.9 … | 317.1 | — | src |
| Multi-GPU x2 · 24 GB | Qwen3.8-27B | Q4_K_M | llama.cpp — | 262144 | 86.3 … | — | 28.0 | src |