Jetson Orin Nano Super / Llama 3.2 3B
Can a Jetson Orin Nano Super run Llama 3.2 3B?
Yes, at a comfortable chat speed. Measured generation speed: 4.3–43.1 tok/s across 3 public runs.
Rule of thumb: 10+ tok/s feels like a chat; 4–10 is usable for assistants and automations; under 4 is batch-job territory. Speeds depend on quantization, runtime, context length and cooling. Check each source.
| Board | Quant | Runtime | Gen tok/s | Prompt tok/s | TTFT ms | Source |
|---|---|---|---|---|---|---|
| Jetson Orin Nano Super Jetson Orin Nano 8GB (Super mode) | INT4 | MLC | 43.1 | – | – | source ↗ 2025-01-16 |
| Jetson Orin Nano Super Jetson Orin Nano Super Dev Kit | not reported | Ollama | 6.31 | – | – | source ↗ 2026-04-24 |
| Jetson Orin Nano Super Jetson Orin Nano Super Dev Kit (CPU only) | not reported | Ollama | 4.3 | – | – | source ↗ 2026-04-24 |
Llama 3.2 3B on other boards
- Jetson AGX Orin 80.4 tok/s best
- Jetson Orin NX 8GB Super 46.5 tok/s best
- Jetson Orin NX 16GB Super 45.8 tok/s best
- Jetson Orin NX 16GB 40.4 tok/s best
- Jetson Orin NX 8GB 34.5 tok/s best
- Jetson Orin Nano 27.7 tok/s best
Buy a Jetson Orin Nano Super
- Jetson Orin Nano Super Developer Kit: $399 raised from $249 (July 2026 report), source ↗ (2026-07-21) Check price (affiliate slot)
Ran Llama 3.2 3B on a Jetson Orin Nano Super? Submit your numbers →