can it run
3.0 GB needed of 13.5 GB usable — headroom for context
~13.5GB usable · Adreno (iGPU) · model file 2.5GB · mini 3.8B
computed roofline: 135.2 GB/s × 0.25–0.80 efficiency window / 2.5GB (Q4_K_M) — bands, never points. Small models (under ~4.5B) run BELOW these bands — kernel-launch overhead keeps them from saturating bandwidth (measured against community medians, 09-06).
→ Tesla M60 (16GB, used) — cheapest catalog machine that runs PHI4 mini 3.8B fully ($35)
→ every model the Adreno X1-45 (Snapdragon X Plus) can run — full list
→explore the full catalog91 machines indexed · live prices · what each one can run