local intelligence

can it run

Can the NVIDIA GeForce RTX 4090 run llava 13B?

FULL

11.1 GB needed of 24 GB usable — headroom for context

24GB · Ada · model file 8.0GB · 13B

~58–96 tok/s

computed roofline: 1008 GB/s × 0.46–0.76 efficiency window / 8.0GB (Q4_K_M) — bands, never points.

Run llava 13B on instead

Tesla P100 (16GB, used) — cheapest catalog machine that runs llava 13B fully ($135)

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 catalog84 machines indexed · live prices · what each one can run
2026-09-17 · ← all models on the NVIDIA GeForce RTX 4090 · fit = weights + 4k KV vs usable memory