Jetson Orin NX 16GB / Gemma 2 9B
Can a Jetson Orin NX 16GB run Gemma 2 9B?
Yes, at a comfortable chat speed. Measured generation speed: 10.56 tok/s across 1 public run.
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 NX 16GB Jetson Orin NX 16GB (original mode) | INT4 | MLC | 10.56 | – | – | source ↗ 2025-01-16 |
Gemma 2 9B on other boards
- Jetson Orin NX 8GB Super 13.38 tok/s best
- Jetson Orin NX 16GB Super 13.26 tok/s best
- Jetson Orin Nano Super 9.2 tok/s best
- Jetson Orin NX 8GB 8.8 tok/s best
- Jetson Orin Nano 7.2 tok/s best
Buy a Jetson Orin NX 16GB
- Jetson Orin NX 16GB module: price not verified yet Check price on Amazon
Ran Gemma 2 9B on a Jetson Orin NX 16GB? Submit your numbers →