can it run
3.2 GB needed of 16 GB usable — headroom for context
16GB · RDNA3 · model file 2.6GB · 4B
computed roofline: 624 GB/s × 0.50–0.75 efficiency window / 2.6GB (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).
→ Tesla M60 (16GB, used) — cheapest catalog machine that runs qwen3 4B fully ($35)
→ rx-7900-xt — the next step up from AMD Radeon RX 7800 XT
→ every model the AMD Radeon RX 7800 XT can run — full list
→explore the full catalog91 machines indexed · live prices · what each one can run