can it run
Yes, but close to the edge. 12GB against a 12GB working set: it runs, with little room for long context windows or other processes.
| model file | 9.1GB (GGUF Q4_K_M) |
| minimum memory | 12GB working set |
| this machine | 12GB GDDR6, 360 GB/s |
| params | 14B |
| license | mit |
| price | $350 |
easy run: ollama pull phi4:14b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ Tesla P40 (24GB, used) — cheapest machine that runs it ($290)
→ ASUS ExpertCenter Pro ET900N G3 (GB300) — this model on the biggest machine
→ every model the RTX 3060 12GB (used) can run — full list