▲ local intelligence

can it run

Can the NVIDIA GeForce RTX 4090 run mistral 7B?

FULL

4.6 GB needed of 24 GB usable — headroom for context

24GB · Ada · model file 4.1GB · 7B

~110–190 tok/s

computed roofline: 1008 GB/s × 0.46–0.76 efficiency window / 4.1GB (Q4_K_M) — bands, never points.

Run mistral 7B on instead

→ Tesla M60 (16GB, used) — cheapest catalog machine that runs mistral 7B fully ($35)

→ rtx-5090 — the next step up from NVIDIA GeForce RTX 4090

→ every model the NVIDIA GeForce RTX 4090 can run — full list

→explore the full catalog91 machines indexed · live prices · what each one can run
2026-10-01 · ← all models on the NVIDIA GeForce RTX 4090 · fit = weights + 4k KV vs usable memory