local intelligence

can it run

Can the NVIDIA B200 192GB run qwen3 14B?

FULL

9.9 GB needed of 192 GB usable — headroom for context

192GB · Blackwell · model file 9.3GB · 14B

~400–650 tok/s

computed roofline: 8000 GB/s × 0.46–0.76 efficiency window / 9.3GB (Q4_K_M) — bands, never points.

Run qwen3 14B on instead

Tesla M60 (16GB, used) — cheapest catalog machine that runs qwen3 14B fully ($35)

NVIDIA DGX Station (GB300) — upgrade path machine

every model the NVIDIA B200 192GB can run — full list

explore the full catalog90 machines indexed · live prices · what each one can run
2026-09-24 · ← all models on the NVIDIA B200 192GB · fit = weights + 4k KV vs usable memory