can it run
Comfortably. 8GB of memory against a 4GB working set leaves headroom for context, the OS, and anything else you're running.
weights 0.9GB + KV cache 2GB at 4k context vs ~6GB usable → full. 2.9 GB needed of 6 GB usable — headroom for context
computed roofline: 68 GB/s × 0.25–0.65 efficiency window / 0.9GB (Q4_K_M) — bands, never points.
| model file | 0.9GB (GGUF Q4_K_M) |
| minimum memory | 4GB working set |
| this machine | 8GB unified |
| params | small |
| license | apache-2.0 |
| price | $499 |
easy run: no stock runtime yet
→ every model the Jetson Orin Nano Super dev kit can run — full list