can it run
Comfortably. 748GB of memory against a 12GB working set leaves headroom for context, the OS, and anything else you're running.
| model file | 9.1GB (GGUF Q4_K_M) |
| minimum memory | 12GB working set |
| this machine | 748GB coherent (252GB HBM3e + 496GB LPDDR5x) |
| params | 14B |
| license | mit |
| price | $94900 |
easy run: ollama pull phi4:14b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ ASUS ExpertCenter Pro ET900N G3 (GB300) — this model on the biggest machine