community-verified · measured pool data
Can the RTX 3060 12GB run Phi-4-reasoning-plus?
Yes — community-measured at 32.7 tok/s (3 runs at 4-bit).
Verified single-stream runs on the RTX 3060 12GB 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 | 32.7 | 2478.1 | — | 4,096 | llama.cpp |