can it run
Comfortably. 12GB of memory against a 4GB working set leaves headroom for context, the OS, and anything else you're running.
| model file | 2.5GB (GGUF Q4_K_M) |
| minimum memory | 4GB working set |
| this machine | 12GB GDDR6, 360 GB/s |
| params | mini 3.8B |
| license | mit |
| price | $350 |
easy run: ollama pull phi4-mini
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ every model the RTX 3060 12GB (used) can run — full list