local intelligence

can it run

Can the Jetson Orin NX (16GB) run qwen3 0.6B?

FULL

1.0 GB needed of 14 GB usable — headroom for context

~14GB usable · Jetson Orin (Ampere iGPU) · model file 0.6GB · 0.6B

~43–94 tok/s

computed roofline: 102.4 GB/s × 0.25–0.55 efficiency window / 0.6GB (Q4_K_M) — bands, never points. Small models (under ~4.5B) run BELOW these bands — kernel-launch overhead keeps them from saturating bandwidth (measured against community medians, 09-06).

Run qwen3 0.6B on instead

Raspberry Pi 5 + AI Kit (Hailo-8L) — cheapest catalog machine that runs qwen3 0.6B fully ($110)

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