community-verified · measured pool data
Can the RTX 3060 12GB ×2 run DeepSeek-R1-Distill-Qwen-7B-GGUF?
Yes — community-measured at 59.7 tok/s (8 runs at 4-bit).
Verified single-stream runs on the RTX 3060 12GB ×2 from the localmaxxing public pool. Every number on this page is measured — nothing here is estimated.
| Quantization | Median tok/s | TTFT (ms) | Peak VRAM | Max context tested | Engines |
|---|---|---|---|---|---|
| 4-bit | 59.7 | 2559.2 | 7.3 GB | 131,072 | llama.cpp |