Jetson Orin Nano Super

Ampere Tegra Embedded SoC LPDDR5 2024

Key Metrics

Launch Date: 2024-12-17
CUDA Cores: 1,024
Memory: 8 GB LPDDR5
Memory Bandwidth: 102.4 GB/s
TDP/TBP: 25 W
Interface: PCIe 4.0 x4

Save this GPU, then open another GPU page to compare them side by side.

GPU Specs

Identity
Entry Type	Other
Official Name	NVIDIA Jetson Orin Nano Super
GPU Codename	GA10B
Architecture	Ampere
Launch Date	2024-12-17
Market Segment Notes	Embedded, SoC in Tegra
Core Specs
GPU Die	GA10B
Process Node	Samsung 8 nm
Die Size	200 mm²
CUDA Cores	1024
SM Count	8
TMUs	32
ROPs	16
AI Units / Tensor Cores	32
Base Clock	1,020 MHz
Boost Clock	1,020 MHz
Pixel Fillrate	16.32 GP/s
Texture Fillrate	32.64 GT/s
FP32 Throughput	2.09 TFLOPS
FP16 Throughput	4.18 TFLOPS
Memory
Memory Size	8 GB
Memory Type	LPDDR5
Memory Bus Width	128-bit
Memory Clock	800 MHz
Memory Bandwidth	102.4 GB/s
L2 Cache	2 MB
L1 Cache	128 KB
Board and Display
TDP / TBP	25 W
Interface	PCIe 4.0 x4
Slot Width	IGP, 70 mm length
Card Length	70 mm
Board Partner Model	Reference or OEM specification
Reference Design	OEM design
Software
CUDA Compute Capability	8.7
Shader Model	6.8
DirectX Support	DirectX 12.2
Vulkan Support	Vulkan 1.4
OpenGL Support	OpenGL 4.6
OpenCL Support	OpenCL 3.0

Why It Mattered

Jetson Orin Nano Super matters as an NVIDIA SoC or embedded platform entry rather than a removable graphics card. Its value is tied to the host board, memory, firmware stack, I/O, and software ecosystem, so exact platform identification is more useful than a broad GPU-family label.

Sources

Independent reference sources

TechPowerUp GPU SpecsModel-level specification reference for this GPU entryOpen source

Reference databases

RightNow GPU DatabaseOpen GPU database used to cross-check specifications A reference database: good for cross-checking specifications, but not proof of the original release details on its own.Open source

Why It Mattered

Jetson AGX Orin 32 GB

Jetson AGX Orin 64 GB

Jetson AGX Xavier 16 GB

Jetson AGX Xavier 32 GB

Independent reference sources

Reference databases