can it run
3.0 GB needed of 6 GB usable — headroom for context
6GB · Turing TU106 · model file 2.5GB · mini 3.8B
computed roofline: 336 GB/s × 0.48–0.72 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).
→ Raspberry Pi 5 + AI Kit (Hailo-8L) — cheapest catalog machine that runs PHI4 mini 3.8B fully ($110)
→ rtx-5060-ti-16 — the next step up from NVIDIA RTX 2060
→ every model the NVIDIA RTX 2060 can run — full list
→explore the full catalog84 machines indexed · live prices · what each one can run