Qwen3-30B-A3B-Thinking-2507
1recorded run
94.3best tok/s
1verified
Fastest GPUs for this model (best tok/s)
- RTX 3060 x294.3
| GPU | Model | Quant | Backend | Ctx | tok/s | prompt tok/s | VRAM GB | Source |
|---|---|---|---|---|---|---|---|---|
| RTX 3060 x2 · 12 GB | Qwen3-30B-A3B-Thinking-2507 | Q4_K_M | llama.cpp b10443 | 65536 | 94.3 ✓ | 1073.4 | 20.1 | src |