can it run
3.8 of 4 GB usable — keep context modest
4GB · Turing · model file 3.3GB · 4B
computed roofline: 128.1 GB/s × 0.48–0.72 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).
→ Tesla M60 (16GB, used) — cheapest catalog machine that runs gemma3 4B fully ($35)
→ gtx-1650-super — the next step up from NVIDIA GeForce GTX 1650
→ every model the NVIDIA GeForce GTX 1650 can run — full list
→explore the full catalog91 machines indexed · live prices · what each one can run