NVIDIA Jetson Orin Nano 8GB vs NVIDIA Jetson Orin Nano Super — Specs & Performance Compared

Verdict: On gemma2:9b, the NVIDIA Jetson Orin Nano Super generates 9.2 tokens/s (per NVIDIA Technical Blog) against 7.2 for the NVIDIA Jetson Orin Nano 8GB (per NVIDIA Developer Blog), best community run on file for each.

Side-by-side APU comparison of the NVIDIA Jetson Orin Nano 8GB and the NVIDIA Jetson Orin Nano Super. Released 2023 (NVIDIA Jetson Orin Nano 8GB), 2024 (NVIDIA Jetson Orin Nano Super). MSRP range: $149 · $249. Specs, synthetic benchmarks, AI inference tok/s, and Amazon availability below; each column header links to that part's benchmark page.

NVIDIA · Jetson Orin

NVIDIA Jetson Orin Nano 8GB

$149 MSRP2023

Full NVIDIA Jetson Orin Nano 8GB benchmarks →

NVIDIA · Jetson Orin

NVIDIA Jetson Orin Nano Super

$249 MSRP2024

Full NVIDIA Jetson Orin Nano Super benchmarks →

*Price sourced from Amazon.com. Price and availability subject to change.

Where to buy

A listing for each part; the current price and stock are on the retailer's page.

Synthetic benchmarks

Each row says whether a higher or a lower number is better (ranks and times are lower-is-better). Scores come from CNX Software, Magazin Mehatronika and Geekbench Browser; each row links its sources, and where they differ the cell shows their median. Empty cells mean we don't yet have that benchmark on file for the SKU.

Benchmark	NVIDIA Jetson Orin Nano 8GB	NVIDIA Jetson Orin Nano Super
7-Zip (higher is better) Source: CNX Software	—	14,820 MIPS
Geekbench 5 multi (higher is better) Source: Magazin Mehatronika	2,866 points	—
Geekbench 5 multi-core (higher is better) Source: Magazin Mehatronika	2,866 points	2,866 points
Geekbench 5 single (higher is better) Source: Magazin Mehatronika	538 points	—
Geekbench 5 single-core (higher is better) Source: Magazin Mehatronika	538 points	538 points
Geekbench 6 multi (higher is better) Source: Geekbench Browser	3,647 points	—
Geekbench 6 single (higher is better) Source: Geekbench Browser	813 points	—
glmark2 OpenGL 4.6 (higher is better) Source: CNX Software	—	2,563 points
glmark2-es2 (higher is better) Source: CNX Software	—	2,488 points

AI inference (tokens/sec)

Top community-reported tokens-per-second results for popular LLMs whose weights fit the card's memory, each linked to its source. See the per-SKU benchmark page for the full set including quantization and prompt length.

NVIDIA Jetson Orin Nano 8GB

qwen2.5:0.5b: 92.9 tok/s (Yuvraj Singh (independent blog benchmark))
llama3.2:1b: 58.0 tok/s (HeyyTechy)
qwen3:0.6b: 49.4 tok/s (SmolHub (Yuvraj Singh))

All NVIDIA Jetson Orin Nano 8GB AI benchmarks →

NVIDIA Jetson Orin Nano Super

llama3.2:1b: 86.5 tok/s (NVIDIA Developer Forums)
llama3.2:1b: 79.0 tok/s (heyytechy.com)
smollm2:1.7b: 64.5 tok/s (NVIDIA Technical Blog)

All NVIDIA Jetson Orin Nano Super AI benchmarks →

Quick answers

Which is better for running local LLMs?

On gemma2:9b, the NVIDIA Jetson Orin Nano Super generates 9.2 tokens/s (per NVIDIA Technical Blog) against 7.2 for the NVIDIA Jetson Orin Nano 8GB (per NVIDIA Developer Blog), best community run on file for each.

What did the NVIDIA Jetson Orin Nano 8GB and the NVIDIA Jetson Orin Nano Super cost at launch?

The NVIDIA Jetson Orin Nano 8GB launched at a $149 MSRP and the NVIDIA Jetson Orin Nano Super at $249. Street prices drift from launch pricing; the Where to buy section links current listings.