▲ local intelligence

can it run

Can the NVIDIA GeForce RTX 2070 Super run qwen3 32B?

NO

21.0 GB vs 8 GB usable — does not fit

8GB · Turing TU104 · model file 20GB · 32B

~11–16 tok/s

computed roofline: 448 GB/s × 0.48–0.72 efficiency window / 20.0GB (Q4_K_M) — bands, never points.

Run qwen3 32B on instead

→ Tesla V100 32GB (used) — cheapest catalog machine that runs qwen3 32B fully ($700)

→ rtx-3060-12 — the next step up from NVIDIA GeForce RTX 2070 Super

→ every model the NVIDIA GeForce RTX 2070 Super can run — full list

→explore the full catalog91 machines indexed · live prices · what each one can run
2026-10-01 · ← all models on the NVIDIA GeForce RTX 2070 Super · fit = weights + 4k KV vs usable memory