DeepSeek-R1-Distill-Qwen-14B
1recorded run
35.1best tok/s
1verified
Fastest GPUs for this model (best tok/s)
- RTX 3060 x235.1
| GPU | Model | Quant | Backend | Ctx | tok/s | prompt tok/s | VRAM GB | Source |
|---|---|---|---|---|---|---|---|---|
| RTX 3060 x2 · 12 GB | DeepSeek-R1-Distill-Qwen-14B | Q4_K_M | llama.cpp 13f2b28 | 512 | 35.1 ✓ | 1123.3 | 16.5 | src |