local intelligence

can it run

Can the NVIDIA GTX 1080 run mistral-nemo 12B?

TIGHT

7.7 of 8 GB usable — keep context modest

8GB · Pascal · model file 7.1GB · 12B

~13–23 tok/s

computed roofline: 320 GB/s × 0.28–0.50 efficiency window / 7.1GB (Q4_K_M) — bands, never points.

Run mistral-nemo 12B on instead

Tesla P100 (16GB, used) — cheapest catalog machine that runs mistral-nemo 12B fully ($135)

rtx-5060-ti-16 — the next step up from NVIDIA GTX 1080

every model the NVIDIA GTX 1080 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 GTX 1080 · fit = weights + 4k KV vs usable memory