can it run
21.0 GB vs 8 GB usable — does not fit
8GB · Turing TU104 · model file 20GB · 32B
computed roofline: 495.9 GB/s × 0.48–0.72 efficiency window / 20.0GB (Q4_K_M) — bands, never points.
→ Tesla V100 32GB (used) — cheapest catalog machine that runs qwen3 32B fully ($700)
→ rtx-3080-10gb — the next step up from NVIDIA GeForce RTX 2080 Super
→ every model the NVIDIA GeForce RTX 2080 Super can run — full list
→explore the full catalog91 machines indexed · live prices · what each one can run