local intelligence

can it run

Can the NVIDIA RTX 3090 run mistral-nemo 12B?

FULL

7.7 GB needed of 24 GB usable — headroom for context

24GB · Ampere GA102 · model file 7.1GB · 12B

~61–100 tok/s

computed roofline: 936 GB/s × 0.46–0.76 efficiency window / 7.1GB (Q4_K_M) — bands, never points.

Community check: ~49 tok/s · 12-15B Q4 · 34 runs · inside our computed band — localmaxxing.com

Run mistral-nemo 12B on instead

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

rtx-5090 — the next step up from NVIDIA RTX 3090

every model the NVIDIA RTX 3090 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 RTX 3090 · fit = weights + 4k KV vs usable memory