can it run
Comfortably. 24GB of memory against a 12GB working set leaves headroom for context, the OS, and anything else you're running.
weights 9.1GB + KV cache 0.78GB at 4k context vs ~22GB usable → full. 9.9 GB needed of 22 GB usable — headroom for context
computed roofline: 273 GB/s × 0.25–0.65 efficiency window / 9.1GB (Q4_K_M) — bands, never points.
| model file | 9.1GB (GGUF Q4_K_M) |
| minimum memory | 12GB working set |
| this machine | 24GB unified LPDDR5X (18-core CPU / 5,120-core GPU base config) |
| params | 14B |
| license | mit |
| price | $2599.99 |
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
→ rtx-5090 — the next step up from this machine's GPU