local intelligence

can it run

Can the NVIDIA Titan X (Pascal) 12GB run qwen3 14B?

TIGHT

9.9 of 12 GB usable — keep context modest

12GB · Pascal · model file 9.3GB · 14B

~14–26 tok/s

computed roofline: 480.4 GB/s × 0.28–0.50 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)

RTX 3090 (24GB, used) — upgrade path machine

every model the NVIDIA Titan X (Pascal) 12GB 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 Titan X (Pascal) 12GB · fit = weights + 4k KV vs usable memory