can it run
9.9 of 12 GB usable — keep context modest
12GB · Ampere · model file 9.1GB · 14B
computed roofline: 912.4 GB/s × 0.46–0.76 efficiency window / 9.1GB (Q4_K_M) — bands, never points.
→ Tesla P100 (16GB, used) — cheapest catalog machine that runs phi4 14B fully ($135)
→ rtx-3090 — the next step up from NVIDIA GeForce RTX 3080 12GB
→ every model the NVIDIA GeForce RTX 3080 12GB can run — full list
→explore the full catalog84 machines indexed · live prices · what each one can run