AI Potluck
Infrastructure / Edge AI hardware

NVIDIA Jetson Orin Nano Super Developer Kit

NVIDIA

Entry-level edge-AI developer kit pairing an 8GB Jetson Orin Nano module with a carrier board, where the Super mode raises throughput to 67 sparse INT8 TOPS. It uses an Ampere GPU with 1024 CUDA cores and 32 tensor cores, a 6-core Arm Cortex-A78AE CPU and 8GB of LPDDR5, and runs small language and vision-language models locally.

The openness axis weighs public datasheets and global availability against an SDK that requires NVIDIA-supplied binary drivers, notwithstanding the community OE4T board support package. Verified 2026-08-13 via the developer-kit page, the Jetson Orin product page and the Jetson Linux developer page.

Openness

3 high confidence
3.0
schematics
partial (carrier design guide public)
toolchain
closed (JetPack/Jetson Linux free but NVIDIA-SLA proprietary)
datasheets
public
blobs
required (proprietary GPU drivers/bootloader required)
retail
open_market (mass-market)

Public datasheets and globally purchasable, but the SDK requires proprietary NVIDIA drivers/blobs under license, so it sits in the documented tier despite the community OE4T BSP. The developer-kit page publishes a datasheet link and directs buyers to worldwide partners, the Jetson Orin family page points designers at the Product Design Guide rather than releasing the kit's own board files, and Jetson Linux 39.2.1 ships its kernel, UEFI bootloader and NVIDIA drivers under the NVIDIA Software License Agreement.

Adoption

4 high confidence
4.0

Widely available developer kit with a large NVIDIA Jetson developer community and global distribution, historically at a low $249 price. The product page no longer prints any price at all, so that $249 figure is no longer confirmable at source. What the page does show is "the most powerful and affordable embedded computer for generative AI. It can be purchased through NVIDIA authorized distributors worldwide", which is the distribution the mass-market reach was banded on.

Capability

3 high confidence
3.0

Solid entry-tier generative-AI compute, but 8GB RAM caps model size versus higher Orin tiers. The spec table reads 67 INT8 TOPS and 8GB 128-bit LPDDR5, against the 157 TOPS / 16GB Orin NX and the 275 TOPS / 64GB AGX Orin on the same family page, which is the entry position in the Orin line.

Verified 2026-08-13