can it run
3.8 GB needed of 24 GB usable — headroom for context
24GB · Ada · model file 3.3GB · 4B
computed roofline: 1008 GB/s × 0.46–0.76 efficiency window / 3.3GB (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 gemma3 4B fully ($110)
→ rtx-5090 — the next step up from NVIDIA GeForce RTX 4090
→ every model the NVIDIA GeForce RTX 4090 can run — full list
→explore the full catalog84 machines indexed · live prices · what each one can run