local intelligence

can it run

Can the Jetson Orin NX (16GB) run llava 13B?

FULL

11.1 GB needed of 14 GB usable — headroom for context

~14GB usable · Jetson Orin (Ampere iGPU) · model file 8.0GB · 13B

~3.2–7 tok/s

computed roofline: 102.4 GB/s × 0.25–0.55 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)

every model the Jetson Orin NX (16GB) can run — full list

explore the full catalog84 machines indexed · live prices · what each one can run
2026-09-17 · ← all models on the Jetson Orin NX (16GB) · fit = weights + 4k KV vs usable memory