local intelligence

can it run

Can the NVIDIA Titan V 12GB run DEEPSEEK-R1 distill 7B?

FULL

4.9 GB needed of 12 GB usable — headroom for context

12GB · Volta · model file 4.7GB · distill 7B

~64–110 tok/s

computed roofline: 652.8 GB/s × 0.46–0.76 efficiency window / 4.7GB (Q4_K_M) — bands, never points.

Run DEEPSEEK-R1 distill 7B on instead

Tesla M60 (16GB, used) — cheapest catalog machine that runs DEEPSEEK-R1 distill 7B fully ($35)

tesla-v100-32gb — the next step up from NVIDIA Titan V 12GB

every model the NVIDIA Titan V 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 V 12GB · fit = weights + 4k KV vs usable memory