local intelligence

can it run

Can the GTX 1650 Mobile run mistral-nemo 12B?

NO

7.7 GB vs 4 GB usable — does not fit

4GB · Turing TU117 · model file 7.1GB · 12B

~8.7–13 tok/s

computed roofline: 128.1 GB/s × 0.48–0.72 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)

every model the GTX 1650 Mobile can run — full list

explore the full catalog84 machines indexed · live prices · what each one can run
2026-09-17 · ← all models on the GTX 1650 Mobile · fit = weights + 4k KV vs usable memory