Jetson Orin NX 8GB / SmolLM2 1.7B

Can a Jetson Orin NX 8GB run SmolLM2 1.7B?

Yes, at a comfortable chat speed. Measured generation speed: 51.5 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.

BoardQuantRuntimeGen tok/sPrompt tok/sTTFT msSource
Jetson Orin NX 8GB
Jetson Orin NX 8GB (original mode)
INT4MLC51.5––source ↗
2025-01-16

SmolLM2 1.7B on other boards

Buy a Jetson Orin NX 8GB

Ran SmolLM2 1.7B on a Jetson Orin NX 8GB? Submit your numbers →

Get the monthly board report

New boards, new runtimes, new numbers. One email a month, no hype.