local intelligence

can it run

Can the NVIDIA GeForce RTX 5070 run DEEPSEEK-R1 distill 14B?

TIGHT

9.8 of 12 GB usable — keep context modest

12GB · Blackwell · model file 9.0GB · distill 14B

~42–60 tok/s

computed roofline: 672 GB/s × 0.56–0.80 efficiency window / 9.0GB (Q4_K_M) — bands, never points.

Community check: ~69 tok/s · 12-15B Q4 · 3 runs · just above our band (15% over the high edge) — localmaxxing.com

Run DEEPSEEK-R1 distill 14B on instead

Tesla P100 (16GB, used) — cheapest catalog machine that runs DEEPSEEK-R1 distill 14B fully ($135)

rtx-5070-ti — the next step up from NVIDIA GeForce RTX 5070

every model the NVIDIA GeForce RTX 5070 can run — full list

explore the full catalog84 machines indexed · live prices · what each one can run
2026-09-17 · ← all models on the NVIDIA GeForce RTX 5070 · fit = weights + 4k KV vs usable memory