NVIDIA Jetson Orin NX 16 GB
NVIDIA graphics card specifications and benchmark scores
Tensor CoresAt a Glance
NVIDIANVIDIA Jetson Orin NX 16 GB Specifications
GPU Core
Shader units and compute resources
The NVIDIA Jetson Orin NX 16 GB GPU core specifications define its raw processing power for graphics and compute workloads. Shading units (also called CUDA cores, stream processors, or execution units depending on manufacturer) handle the parallel calculations required for rendering. TMUs (Texture Mapping Units) process texture data, while ROPs (Render Output Units) handle final pixel output. Higher shader counts generally translate to better GPU benchmark performance, especially in demanding games and 3D applications.
Jetson Orin NX 16 GB Clock Speeds
GPU and memory frequencies
Clock speeds directly impact the Jetson Orin NX 16 GB's performance in GPU benchmarks and real-world gaming. The base clock represents the minimum guaranteed frequency, while the boost clock indicates peak performance under optimal thermal conditions. Memory clock speed affects texture loading and frame buffer operations. The Jetson Orin NX 16 GB by NVIDIA dynamically adjusts frequencies based on workload, temperature, and power limits to maximize performance while maintaining stability.
NVIDIA's Jetson Orin NX 16 GB Memory
VRAM capacity and bandwidth
VRAM (Video RAM) is dedicated memory for storing textures, frame buffers, and shader data. The Jetson Orin NX 16 GB's memory capacity determines how well it handles high-resolution textures and multiple displays. Memory bandwidth, measured in GB/s, affects how quickly data moves between the GPU and VRAM. Higher bandwidth improves performance in memory-intensive scenarios like 4K gaming. The memory bus width and type (GDDR6, GDDR6X, HBM) significantly influence overall GPU benchmark scores.
Jetson Orin NX 16 GB by NVIDIA Cache
On-chip cache hierarchy
On-chip cache provides ultra-fast data access for the Jetson Orin NX 16 GB, reducing the need to fetch data from slower VRAM. L1 and L2 caches store frequently accessed data close to the compute units. AMD's Infinity Cache (L3) dramatically increases effective bandwidth, improving GPU benchmark performance without requiring wider memory buses. Larger cache sizes help maintain high frame rates in memory-bound scenarios and reduce power consumption by minimizing VRAM accesses.
Jetson Orin NX 16 GB Theoretical Performance
Compute and fill rates
Theoretical performance metrics provide a baseline for comparing the NVIDIA Jetson Orin NX 16 GB against other graphics cards. FP32 (single-precision) performance, measured in TFLOPS, indicates compute capability for gaming and general GPU workloads. FP64 (double-precision) matters for scientific computing. Pixel and texture fill rates determine how quickly the GPU can render complex scenes. While real-world GPU benchmark results depend on many factors, these specifications help predict relative performance levels.
Jetson Orin NX 16 GB Ray Tracing & AI
Hardware acceleration features
The NVIDIA Jetson Orin NX 16 GB includes dedicated hardware for ray tracing and AI acceleration. RT cores handle real-time ray tracing calculations for realistic lighting, reflections, and shadows in supported games. Tensor cores (NVIDIA) or XMX cores (Intel) accelerate AI workloads including DLSS, FSR, and XeSS upscaling technologies. These features enable higher visual quality without proportional performance costs, making the Jetson Orin NX 16 GB capable of delivering both stunning graphics and smooth frame rates in modern titles.
Ampere Architecture & Process
Manufacturing and design details
The NVIDIA Jetson Orin NX 16 GB is built on NVIDIA's Ampere architecture, which defines how the GPU processes graphics and compute workloads. The manufacturing process node affects power efficiency, thermal characteristics, and maximum clock speeds. Smaller process nodes pack more transistors into the same die area, enabling higher performance per watt. Understanding the architecture helps predict how the Jetson Orin NX 16 GB will perform in GPU benchmarks compared to previous generations.
Power & Thermal
TDP and power requirements
Power specifications for the NVIDIA Jetson Orin NX 16 GB determine PSU requirements and thermal management needs. TDP (Thermal Design Power) indicates the heat output under typical loads, guiding cooler selection. Power connector requirements ensure adequate power delivery for stable operation during demanding GPU benchmarks. The suggested PSU wattage accounts for the entire system, not just the graphics card. Efficient power delivery enables the Jetson Orin NX 16 GB to maintain boost clocks without throttling.
Jetson Orin NX 16 GB by NVIDIA Physical & Connectivity
Dimensions and outputs
Physical dimensions of the NVIDIA Jetson Orin NX 16 GB are critical for case compatibility. Card length, height, and slot width determine whether it fits in your chassis. The PCIe interface version affects bandwidth for communication with the CPU. Display outputs define monitor connectivity options, with modern cards supporting multiple high-resolution displays simultaneously. Verify these specifications against your case and motherboard before purchasing to ensure a proper fit.
NVIDIA API Support
Graphics and compute APIs
API support determines which games and applications can fully utilize the NVIDIA Jetson Orin NX 16 GB. DirectX 12 Ultimate enables advanced features like ray tracing and variable rate shading. Vulkan provides cross-platform graphics capabilities with low-level hardware access. OpenGL remains important for professional applications and older games. CUDA (NVIDIA) and OpenCL enable GPU compute for video editing, 3D rendering, and scientific applications. Higher API versions unlock newer graphical features in GPU benchmarks and games.
Jetson Orin NX 16 GB Product Information
Release and pricing details
The NVIDIA Jetson Orin NX 16 GB is manufactured by NVIDIA as part of their graphics card lineup. Release date and launch pricing provide context for comparing GPU benchmark results with competing products from the same era. Understanding the product lifecycle helps evaluate whether the Jetson Orin NX 16 GB by NVIDIA represents good value at current market prices. Predecessor and successor information aids in tracking generational improvements and planning future upgrades.
About NVIDIA Jetson Orin NX 16 GB
The NVIDIA Jetson Orin NX 16 GB is an embedded system-on-module built on the Ampere architecture, fabricated on Samsung's 8 nm process with a 200 mm² die. It integrates 1024 shading units, 32 tensor cores, and 16 GB of LPDDR5 memory across a 128-bit bus, all within a 25 W thermal envelope. The module measures 70 mm by 45 mm and is marked as end-of-life. Its launch MSRP was 599 USD. This analysis draws exclusively from the specification data provided, interpreting its position in the database and its theoretical performance characteristics.
How It Compares
The fact pack does not include any nearestRivals entries, so a direct head-to-head comparison against specific GPUs is not possible from the available data. Instead, the percentileVsAllGpus field places this device at the 50th percentile of all GPUs tracked in the database. That means it sits exactly at the median: half of the GPUs in the database are slower, and half are faster. This is a useful reference point, though it is derived from the database's overall population, not from a set of nearest rivals.
Within the embedded category, the Jetson Orin NX 16 GB distinguishes itself through memory capacity: 16 GB of LPDDR5 on a 128-bit bus yields 102.4 GB/s of bandwidth. This is a high capacity for a 25 W module, and it pairs with a compute throughput of 1.880 TFLOPS FP32 and 3.760 TFLOPS FP16 (2:1). The 2:1 FP16 ratio indicates that the architecture can double its throughput when using half-precision operations, which is common for AI inference workloads. The pixel rate of 14.69 GPixel/s and texture rate of 29.38 GTexel/s define its rasterization limits, but these are modest compared to discrete desktop parts.
As an end-of-life product, the Jetson Orin NX 16 GB is no longer in active production. The absence of a successor in the fact pack means its position in the database is static. The 50th percentile ranking, combined with a 25 W TDP, suggests it occupies a niche where power efficiency is more important than raw performance. The lack of dedicated RT cores (rtCores is null) further distinguishes it from desktop Ampere cards that include ray tracing hardware.
Ray Tracing and Feature Set
The Jetson Orin NX 16 GB does not include dedicated ray tracing cores. The rtCores field is null, meaning hardware-accelerated ray tracing is not available. This is a critical distinction from other Ampere-based GPUs that do have RT cores. However, the API support is comprehensive: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. DirectX 12 Ultimate includes features like DXR (DirectX Raytracing) and variable rate shading, but without RT cores, any ray-traced effects would have to be computed via compute shaders, which is inefficient. The presence of 32 tensor cores does provide hardware acceleration for AI tasks, though the fact pack does not specify which AI features are enabled.
The memory subsystem is a key strength: 16 GB of LPDDR5 on a 128-bit bus delivers 102.4 GB/s. The memory clock is 800 MHz (6.4 Gbps effective). This bandwidth is sufficient for many embedded vision and inference workloads. The bus interface is PCIe 4.0 x4, which allows for moderate host connectivity. Display outputs are marked as "Portable Device Dependent," meaning the module does not have fixed display connectors; it relies on the carrier board.
The process node is 8 nm at Samsung, with a die size of 200 mm². The architecture is Ampere, and the chip is GA10B. This is a system-on-module, not a discrete GPU, so it integrates CPU, GPU, and memory controller. The slot width is IGP, indicating an integrated graphics processor.
Benchmark Performance
The fact pack does not include any benchmark scores; the avgBenchmarkScore field is 0, and the benchmarks array is empty. Therefore, all performance analysis must rely on the specification-derived metrics. The FP32 throughput of 1.880 TFLOPS is a raw measure of single-precision compute. The FP16 throughput of 3.760 TFLOPS (2:1) shows that half-precision operations run at double speed, which is typical for Ampere and beneficial for neural network inference. The pixel rate of 14.69 GPixel/s and texture rate of 29.38 GTexel/s are derived from the 16 ROPs and 32 TMUs, respectively, though the fact pack does not list those components explicitly; it lists 32 TMUs and 16 ROPs. The shading units number 1024.
Given the 50th percentile ranking, the Jetson Orin NX 16 GB performs better than half of the GPUs in the database. However, that percentile is likely based on a composite score that includes many desktop and mobile GPUs. For an embedded module, the performance is respectable, but it is not competitive with high-end discrete cards. The lack of RT cores means that any ray-traced benchmark would show very low performance, as it would rely on compute shaders.
In practical terms, the 102.4 GB/s memory bandwidth is a limiting factor for some workloads. The FP32 throughput of 1.880 TFLOPS suggests that the compute-to-bandwidth ratio is balanced for edge inference, where memory access patterns are often streaming. The 16 GB capacity allows larger models to reside on-chip, avoiding frequent host transfers. The 25 W TDP means that sustained performance is constrained by thermal limits, but the module is designed for passive cooling in many applications.
The absence of benchmark data means that we cannot provide exact frame rates or relative deltas. The theoretical numbers give a baseline: the pixel rate of 14.69 GPixel/s and texture rate of 29.38 GTexel/s are raw fill-rate figures. They indicate the maximum rate at which the rasterizer can process pixels and texels, respectively, but real-world performance depends on many other factors.
FAQ
Q: Does the NVIDIA Jetson Orin NX 16 GB support hardware ray tracing?
A: No. The rtCores field is null, indicating that no dedicated ray tracing cores are present. Ray-traced effects would have to be computed via general-purpose shaders.
Q: What is the memory bandwidth of this module?
A: The memory bandwidth is 102.4 GB/s, achieved with 16 GB of LPDDR5 on a 128-bit bus. The memory clock is 800 MHz (6.4 Gbps effective).
Q: What is the launch MSRP of the Jetson Orin NX 16 GB?
A: The launch MSRP was 599 USD.
Q: What API versions are supported?
A: It supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.
Q: How many tensor cores are included?
A: There are 32 tensor cores, which provide hardware acceleration for AI and deep learning workloads.
Q: Is this product still in production?
A: No. The production status is marked as "End-of-life."
Who Should Consider It
The Jetson Orin NX 16 GB is designed for embedded and edge applications where power consumption is critical. The 25 W TDP and compact 70 mm x 45 mm footprint make it suitable for drones, robotics, and portable AI devices. The 16 GB memory capacity is generous for an embedded module, allowing large neural network models to be loaded entirely on the device. The 32 tensor cores are the key asset for AI inference, and the 3.760 TFLOPS FP16 throughput is well-suited for half-precision workloads.
For graphics rendering, the pixel rate of 14.69 GPixel/s and texture rate of 29.38 GTexel/s suggest that it can handle moderate resolutions at modest settings, but it lacks the raw power for high refresh rates or high-resolution gaming. The absence of RT cores means that modern games with ray-traced effects will not run well, even if the API supports DXR. Users who need ray tracing should look elsewhere. The 50th percentile ranking indicates that it is a mid-pack performer in the database, but that ranking includes many discrete GPUs; within the embedded class, it is a strong option.
Since the product is end-of-life, it may be available in the secondary market, but the fact pack does not provide current pricing. For new designs, consider whether the Ampere architecture's feature set meets your needs. The PCIe 4.0 x4 interface provides reasonable host connectivity, and the portable device-dependent display outputs require a custom carrier board. Overall, this module is a capable choice for AI-centric edge computing, but not for gaming or ray-traced graphics.
Detailed benchmark scores and charts for the NVIDIA Jetson Orin NX 16 GB are below.
Benchmark Scores
No benchmark data available for this GPU.
Compare with Other GPUs
Select another GPU to compare specifications and benchmarks side-by-side.
Browse GPUs