Qwen3-1.7B
1recorded run
198.1best tok/s
1verified
Fastest GPUs for this model (best tok/s)
- RTX 3060 x2198.1
| GPU | Model | Quant | Backend | Ctx | tok/s | prompt tok/s | VRAM GB | Source |
|---|---|---|---|---|---|---|---|---|
| RTX 3060 x2 · 12 GB | Qwen3-1.7B | Q4_K_M | llama.cpp 13f2b28 | 512 | 198.1 ✓ | 7121.2 | 6.7 | src |