Boards / Jetson Orin Nano

Jetson Orin Nano (original / mode not stated): LLM benchmarks

Orin Nano results in the original power mode, or where the source did not state the mode.

At a glance

  • Measured runs16
  • Models tested13
  • Fastest run54.8 tok/s
  • Llama 3.2 1B, INT4, MLC 0.1.2 (dustynv/mlc:0.1.2-r36.3.0) · source ↗
  • Sources4

Where to buy

  • Jetson Orin Nano Developer Kit (same hardware, original power mode): $399 same dev kit as Super; Super mode is a JetPack 6.2 flash, source ↗ (2026-07-21) Check price on Amazon

Every run on this board

ModelQuantRuntimeGen tok/sPrompt tok/sTTFT msSource
Llama 3.2 1BINT4MLC 0.1.2 (dustynv/mlc:0.1.2-r36.3.0)54.8––source ↗
accessed 2026-10-17
SmolLM2 1.7BINT4MLC41––source ↗
2025-01-16
Gemma 4 E2Bnot statednot stated34––source ↗
2026-08-25
Llama 3.2 3BINT4MLC27.7––source ↗
2025-01-16
Phi-3.5 3.8BINT4MLC24.7––source ↗
2025-01-16
Gemma 2 2BINT4MLC21.5––source ↗
2025-01-16
Qwen3.5 4Bnot statednot stated18––source ↗
2026-08-25
Gemma 4 E4Bnot statednot stated17––source ↗
2026-08-25
Vinci Piccolo 1.0 (Qwen3.5-4B based)Q4_K_Mllama.cpp14.77––source ↗
2026-10-05
Qwen2.5 7BINT4MLC14.2––source ↗
2025-01-16
Llama 3.1 8BINT4MLC14––source ↗
2025-01-16
Vinci Piccolo 1.0 (Qwen3.5-4B based)Q4_K_Mllama.cpp13.98––source ↗
2026-10-05
Vinci Piccolo 1.0 (Qwen3.5-4B based)Q4_K_Mllama.cpp13.41––source ↗
2026-10-05
Vinci Piccolo 1.0 (Qwen3.5-4B based)Q4_K_Mllama.cpp13.19––source ↗
2026-10-05
Qwen3.5 9Bnot statednot stated12––source ↗
2026-08-25
Gemma 2 9BINT4MLC7.2––source ↗
2025-01-16

Can the Jetson Orin Nano run…

Can it run Gemma 2 2B?Can it run Gemma 2 9B?Can it run Gemma 4 E2B?Can it run Gemma 4 E4B?Can it run Llama 3.1 8B?Can it run Llama 3.2 1B?Can it run Llama 3.2 3B?Can it run Phi-3.5 3.8B?Can it run Qwen2.5 7B?Can it run Qwen3.5 4B?Can it run Qwen3.5 9B?Can it run SmolLM2 1.7B?Can it run Vinci Piccolo 1.0?

Have this board? Submit your own run →

Get the monthly board report

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