NVIDIA Jetson Orin Nano Super vs NVIDIA RTX 6000D Comparison

Where Each One Wins

The recorded data splits these two NVIDIA products into entirely different performance classes. The NVIDIA Jetson Orin Nano Super occupies the embedded, low-power segment, while the NVIDIA RTX 6000D sits at the top of the professional workstation and datacenter tier. The use-case split is stark: one is a compact system-on-module for edge deployments, the other is a massive dual-slot accelerator for heavy compute workloads.

The Jetson Orin Nano Super uses the GA10B chip on Samsung's 8 nm process, drawing 25 W. Its form factor is an integrated graphics processor (IGP) with dimensions of 70 mm by 45 mm, making it suitable for portable devices and embedded applications. It has no dedicated benchmark entries in the database, and its percentile ranking sits at 50, indicating it lands in the middle of all GPUs tracked. Its average benchmark score is recorded as zero, which reflects the absence of standardized test data rather than a literal lack of compute capability.

The RTX 6000D, by contrast, is a 600 W dual-slot card measuring 304 mm by 137 mm by 40 mm. It uses the GB202 chip on TSMC's 5 nm process. The database records two benchmark results: a 3DMark Steel Nomad DX12 score of 3522 and a Geekbench OpenCL score of 388405. Its average benchmark score across those tests is 195964, placing it in the 98th percentile of all GPUs. This percentile ranking indicates it outperforms the vast majority of recorded devices.

The use-case split is therefore clear. The Jetson Orin Nano Super wins in scenarios requiring low power draw, compact physical footprint, and integration into portable or embedded systems. The RTX 6000D wins decisively in raw compute, memory capacity, and bandwidth. The data shows no overlap in their intended operating environments.

Architecture Differences

The two processors come from different architectural generations and foundries. The Jetson Orin Nano Super uses the Ampere architecture, built on Samsung's 8 nm process. Its die size is 200 mm². The transistor count is listed as unknown. The RTX 6000D uses the Blackwell 2.0 architecture, built on TSMC's 5 nm process. Its die size is 750 mm², and it packs 92,200 million transistors, giving a transistor density of 122.9 million per square millimeter.

The shader configuration differs dramatically. The Jetson Orin Nano Super has 1024 shading units, 32 texture mapping units (TMUs), 16 raster output units (ROPs), and 32 tensor cores. It has no dedicated RT cores listed. The RTX 6000D has 19,968 shading units, 624 TMUs, 192 ROPs, 156 RT cores, and 624 tensor cores. This represents a roughly 19.5-fold difference in shading units and a 19.5-fold difference in tensor cores.

Memory architecture also diverges. The Jetson Orin Nano Super uses 8 GB of LPDDR5 on a 128-bit bus, with memory clocked at 800 MHz (6.4 Gbps effective). Bandwidth is 102.4 GB/s. The RTX 6000D uses 84 GB of GDDR7 on a 448-bit bus, with memory clocked at 1560 MHz (25 Gbps effective). Bandwidth reaches 1.40 TB/s, which is roughly 13.7 times higher than the Jetson's figure.

The RTX 6000D includes RT cores for hardware-accelerated ray tracing, while the Jetson Orin Nano Super lists none. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The bus interface differs: the Jetson uses PCIe 4.0 x4, while the RTX 6000D uses PCIe 5.0 x16. The RTX 6000D has four DisplayPort 2.1b outputs, whereas the Jetson's display outputs are listed as portable device dependent.

The process node difference (8 nm versus 5 nm) and the foundry difference (Samsung versus TSMC) indicate distinct manufacturing approaches. The RTX 6000D's transistor density of 122.9M per mm² reflects the more advanced 5 nm node, while the Jetson's density is not recorded.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark results between these two products. The wins counter shows zero for both sides. However, the RTX 6000D has its own benchmark scores, and its nearest rivals provide context for its performance level.

The RTX 6000D scores 3522 in 3DMark Steel Nomad DX12 and 388405 in Geekbench OpenCL. Its average benchmark score is 195964. Its nearest rival, the NVIDIA Tesla V100S PCIe 32 GB, has an average score of 194415, which is 0.8 percent lower. The NVIDIA A100 SXM4 40 GB scores 187147, 4.7 percent lower. The NVIDIA RTX 5000 Ada Generation scores 184664, 6.1 percent lower. The NVIDIA A100 PCIe 80 GB scores 207124, which is 5.4 percent higher than the RTX 6000D.

These deltas show the RTX 6000D sits within a tight band of high-end accelerators. It edges out the Tesla V100S by a narrow margin, leads the A100 SXM4 by nearly five percent, and trails the A100 PCIe 80 GB by just over five percent. The RTX 5000 Ada Generation trails by six percent. This places the RTX 6000D in a competitive position among flagship compute cards, though not at the absolute top.

The Jetson Orin Nano Super has no recorded benchmark scores, so no numerical comparison can be made directly. Its percentile rank of 50 versus the RTX 6000D's 98 indicates a wide gap in measured performance relative to the full database. The Jetson's FP32 throughput is 2.089 TFLOPS, while the RTX 6000D delivers 97.04 TFLOPS, a 46.5-fold difference. FP16 performance is 4.178 TFLOPS for the Jetson versus 97.04 TFLOPS for the RTX 6000D, a 23.2-fold difference.

The pixel rate and texture rate also show massive gaps. The Jetson produces 16.32 GPixel/s and 32.64 GTexel/s. The RTX 6000D produces 466.6 GPixel/s and 1,516.3 GTexel/s. These are 28.6-fold and 46.5-fold differences, respectively.

The Verdict

The data indicates these products serve fundamentally different purposes, and neither can substitute for the other. The NVIDIA Jetson Orin Nano Super is an embedded computing module with a 25 W power envelope, compact dimensions, and a 50th percentile performance ranking. It targets portable devices, edge inference, and low-power applications where physical size and energy consumption are primary constraints.

The NVIDIA RTX 6000D is a professional workstation accelerator with a 600 W power envelope, dual-slot cooling, and a 98th percentile ranking. It delivers 97.04 TFLOPS of FP32 performance, 84 GB of GDDR7 memory, and 1.40 TB/s of bandwidth. Its benchmark scores place it among the top accelerators in the database, slightly ahead of the Tesla V100S and A100 SXM4, and slightly behind the A100 PCIe 80 GB.

The choice between these two depends entirely on the workload environment. For embedded systems with tight power budgets and space constraints, the Jetson Orin Nano Super is the only viable option given its 25 W TDP and IGP form factor. For high-performance compute, rendering, or AI training workloads requiring maximum throughput, the RTX 6000D is the clear choice, with its 46.5-fold FP32 advantage and 13.7-fold bandwidth advantage over the Jetson.

The RTX 6000D's launch MSRP is 8,565 USD. The Jetson Orin Nano Super's launch MSRP is 249 USD. The price difference reflects the enormous gap in compute resources, memory capacity, and manufacturing complexity.

FAQ

Q: How does the memory bandwidth compare between the two?

A: The Jetson Orin Nano Super provides 102.4 GB/s of bandwidth from 8 GB of LPDDR5 on a 128-bit bus. The RTX 6000D provides 1.40 TB/s from 84 GB of GDDR7 on a 448-bit bus, a roughly 13.7-fold difference.

Q: What is the FP32 compute difference?

A: The Jetson Orin Nano Super delivers 2.089 TFLOPS of FP32 performance. The RTX 6000D delivers 97.04 TFLOPS, which is approximately 46.5 times higher.

Q: Which product has a higher percentile ranking in the database?

A: The RTX 6000D ranks in the 98th percentile of all GPUs, while the Jetson Orin Nano Super ranks in the 50th percentile.

Q: What benchmark scores does the RTX 6000D have?

A: The RTX 6000D scores 3522 in 3DMark Steel Nomad DX12 and 388405 in Geekbench OpenCL, giving an average benchmark score of 195964.

Q: What are the nearest rivals to the RTX 6000D?

A: The nearest rivals are the NVIDIA Tesla V100S PCIe 32 GB (0.8 percent lower), NVIDIA A100 SXM4 40 GB (4.7 percent lower), NVIDIA A100 PCIe 80 GB (5.4 percent higher), and NVIDIA RTX 5000 Ada Generation (6.1 percent lower).

Q: Does the Jetson Orin Nano Super have RT cores?

A: The database lists no RT cores for the Jetson Orin Nano Super. The RTX 6000D has 156 RT cores.

Specification Differences

| Field | NVIDIA Jetson Orin Nano Super | NVIDIA RTX 6000D |

|-------|-------------------------------|------------------|

| Chip | GA10B | GB202 |

| Architecture | Ampere | Blackwell 2.0 |

| Generation | Tegra (Ampere) | Blackwell PRO W (x000) |

| Process Node | 8 nm | 5 nm |

| Foundry | Samsung | TSMC |

| Die Size | 200 mm² | 750 mm² |

| Transistors | unknown | 92,200 million |

| Transistor Density | null | 122.9M / mm² |

| Base Clock | null | 1992 MHz |

| Boost Clock | null | 2430 MHz |

| Memory Clock | 800 MHz 6.4 Gbps effective | 1560 MHz 25 Gbps effective |

| Memory Size | 8 GB | 84 GB |

| Memory Type | LPDDR5 | GDDR7 |

| Memory Bus Width | 128 bit | 448 bit |

| Memory Bandwidth | 102.4 GB/s | 1.40 TB/s |

| Shading Units | 1024 | 19968 |

| TMUs | 32 | 624 |

| ROPs | 16 | 192 |

| RT Cores | null | 156 |

| Tensor Cores | 32 | 624 |

| Pixel Rate | 16.32 GPixel/s | 466.6 GPixel/s |

| Texture Rate | 32.64 GTexel/s | 1,516.3 GTexel/s |

| FP32 | 2.089 TFLOPS | 97.04 TFLOPS |

| FP16 | 4.178 TFLOPS (2:1) | 97.04 TFLOPS (1:1) |

| TDP | 25 W | 600 W |

| Slot Width | IGP | Dual-slot |

| Power Connectors | null | 1x 16-pin |

| Suggested PSU | null | 1000 W |

| Bus Interface | PCIe 4.0 x4 | PCIe 5.0 x16 |

| Display Outputs | Portable Device Dependent | 4x DisplayPort 2.1b |

| Dimensions | 70 mm 2.8 inches, 45 mm 1.8 inches | 304 mm 12 inches, 137 mm 5.4 inches, 40 mm 1.6 inches |

| Release Date | 2024-12-16 | 2025-07-13 |

| Predecessor | null | Workstation Ada |

| Launch MSRP | 249 USD | 8,565 USD |

| Percentile vs All GPUs | 50 | 98 |

| Avg Benchmark Score | 0 | 195964 |