can it run
1.0 GB needed of 24 GB usable — headroom for context
24GB · Ampere GA102 · model file 0.6GB · 0.6B
computed roofline: 936 GB/s × 0.46–0.76 efficiency window / 0.6GB (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 qwen3 0.6B fully ($110)
→ rtx-5090 — the next step up from NVIDIA RTX 3090
→ every model the NVIDIA RTX 3090 can run — full list
→explore the full catalog84 machines indexed · live prices · what each one can run