NVIDIA Jetson Orin Nano Super vs NVIDIA RTX PRO 4000 Blackwell Comparison

NVIDIA
GEFORCE

NVIDIA Jetson Orin Nano Super

CORE STATE GA10B
VRAM 8 GB
CLOCK SPEED —
TDP 25 W
BUS WIDTH 128 bit
ARCHITECTURE Ampere
nm
PROCESS 8 nm
LAUNCH DATE 2024
VS
NVIDIA
GEFORCE

RTX PRO 4000 Blackwell

CORE STATE GB203
VRAM 24 GB
CLOCK SPEED 2055 MHz
TDP 140 W
BUS WIDTH 192 bit
ARCHITECTURE Blackwell 2.0
nm
PROCESS 5 nm
LAUNCH DATE 2025

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
N/A
4,648
geekbench_vulkan
N/A
194,168
passmark_directx_10
N/A
173
passmark_directx_11
N/A
276
passmark_directx_12
N/A
97
passmark_directx_9
N/A
354
passmark_g2d
N/A
1,265
passmark_g3d
N/A
28,427
passmark_gpu_compute
N/A
14,805

Analysis: NVIDIA Jetson Orin Nano Super vs NVIDIA RTX PRO 4000 Blackwell

The Verdict

The recorded data presents a stark contrast between two NVIDIA products aimed at entirely different workloads. The Jetson Orin Nano Super is a compact, low-power edge computing module with a 50th percentile ranking among all GPUs, while the RTX PRO 4000 Blackwell is a professional workstation card that sits at the 72nd percentile. The RTX PRO 4000 Blackwell delivers dominant performance across every measurable benchmark category, with an average benchmark score of 27,135 compared to the Jetson Orin Nano Super's lack of recorded benchmark scores. The Jetson Orin Nano Super targets embedded and robotics applications where its 25 W power envelope and small footprint matter more than raw throughput. The RTX PRO 4000 Blackwell, with its 140 W TDP and single-slot design, is for desktop workstation environments that need substantial compute capability. Users should select the Jetson Orin Nano Super for portable, power-constrained deployments, while the RTX PRO 4000 Blackwell is the clear choice for professional 3D rendering, simulation, and compute-heavy tasks where performance is the priority.

Architecture Differences

The two chips come from different manufacturing generations and foundries. The Jetson Orin Nano Super uses the GA10B chip built on Samsung's 8 nm process with a die size of 200 mm². The RTX PRO 4000 Blackwell uses the GB203 chip built on TSMC's 5 nm process with a die size of 378 mm² and 45,600 million transistors, yielding a transistor density of 120.6M per mm². The Jetson Orin Nano Super's transistor count is listed as unknown, which limits direct density comparisons.

Architecturally, the Jetson Orin Nano Super is based on the Ampere architecture, while the RTX PRO 4000 Blackwell uses Blackwell 2.0. This generational gap shows up in several feature differences. The RTX PRO 4000 Blackwell includes 70 dedicated ray tracing cores and 280 tensor cores, whereas the Jetson Orin Nano Super has 32 tensor cores and no recorded ray tracing core count. The Jetson Orin Nano Super has 1,024 shading units, 32 texture mapping units, and 16 raster output units. The RTX PRO 4000 Blackwell has 8,960 shading units, 280 TMUs, and 96 ROPs, which are 8.75x, 8.75x, and 6x greater respectively.

Memory architecture also diverges significantly. The Jetson Orin Nano Super pairs 8 GB of LPDDR5 memory with a 128-bit bus and 102.4 GB/s bandwidth. The RTX PRO 4000 Blackwell uses 24 GB of GDDR7 memory on a 192-bit bus delivering 672.0 GB/s bandwidth. Clock behavior differs as well: the Jetson Orin Nano Super has no base or boost clock figures recorded, only a memory clock of 800 MHz (6.4 Gbps effective), while the RTX PRO 4000 Blackwell lists a 1230 MHz base clock and 2055 MHz boost clock. The API support is identical for DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so software compatibility is not a differentiator.

Head-to-Head Benchmarks

The benchmark data includes results only for the RTX PRO 4000 Blackwell, as the Jetson Orin Nano Super has an empty benchmarks array. The RTX PRO 4000 Blackwell's performance profile is therefore the sole quantitative reference. In 3DMark Steel Nomad DX12, it scores 4,648. Geekbench Vulkan shows 194,168. Passmark results break down across DirectX versions: 173 for DirectX 10, 276 for DirectX 11, 97 for DirectX 12, and 354 for DirectX 9. The Passmark G2D score is 1,265, while the G3D score reaches 28,427. GPU compute performance is recorded at 14,805.

Relative to its nearest rivals, the RTX PRO 4000 Blackwell sits within a tight band. It trails the AMD Radeon RX 6700 XT by 1.1% (that card averages 27,425), trails the NVIDIA GeForce RTX 4070 Mobile by 1.1% (27,435), and trails the NVIDIA GeForce RTX 3090 by 1.6% (27,565). It leads the NVIDIA RTX A4000 by 1.7% (that card averages 26,683). The average benchmark score of 27,135 places it slightly below the RX 6700 XT and RTX 4070 Mobile but above the RTX A4000. Since the Jetson Orin Nano Super has no recorded benchmark scores, no direct head-to-head numbers exist; the data only shows that the RTX PRO 4000 Blackwell occupies a mid-to-high tier among all GPUs, while the Jetson Orin Nano Super sits at the exact median.

The wins count shows 0 wins for the Jetson Orin Nano Super and 0 wins for the RTX PRO 4000 Blackwell, which reflects the absence of head-to-head benchmark entries rather than a tie in performance. The RTX PRO 4000 Blackwell's raw compute figures dwarf the Jetson Orin Nano Super's: FP32 performance is 36.83 TFLOPS versus 2.089 TFLOPS, a factor of roughly 17.6x. FP16 performance is 36.83 TFLOPS (1:1) versus 4.178 TFLOPS (2:1), a factor of about 8.8x. Pixel rate is 197.3 GPixel/s versus 16.32 GPixel/s, and texture rate is 575.4 GTexel/s versus 32.64 GTexel/s.

Specification Differences

The two products differ across nearly every specification field. The process node shifts from 8 nm (Samsung) to 5 nm (TSMC), and the die size grows from 200 mm² to 378 mm². The RTX PRO 4000 Blackwell lists 45,600 million transistors; the Jetson Orin Nano Super's count is unknown. Base and boost clocks appear only on the RTX PRO 4000 Blackwell (1230 MHz and 2055 MHz). Memory size jumps from 8 GB LPDDR5 to 24 GB GDDR7, with bus width expanding from 128 bit to 192 bit. Bandwidth more than sextuples from 102.4 GB/s to 672.0 GB/s. Shading units increase from 1,024 to 8,960, TMUs from 32 to 280, ROPs from 16 to 96. Tensor cores rise from 32 to 280, and the RTX PRO 4000 Blackwell adds 70 ray tracing cores where the Jetson Orin Nano Super records none.

Power draw differs by 115 W: 25 W versus 140 W. The Jetson Orin Nano Super is an integrated graphics processor (IGP) with no power connector listed, while the RTX PRO 4000 Blackwell is a single-slot card with one 16-pin connector and a 300 W suggested PSU. Bus interface changes from PCIe 4.0 x4 to PCIe 5.0 x16. Display outputs are "Portable Device Dependent" on the Jetson, while the RTX PRO 4000 Blackwell has 4x DisplayPort 2.1b. Physical dimensions diverge sharply: the Jetson measures 70 mm by 45 mm, while the RTX PRO 4000 Blackwell measures 241 mm by 111 mm by 20 mm. Release dates differ by three months: the Jetson launched on 2024-12-16, the RTX PRO 4000 Blackwell on 2025-03-17. The RTX PRO 4000 Blackwell lists a predecessor (Workstation Ada), while the Jetson has none. The Jetson has a launch MSRP of 249 USD; the RTX PRO 4000 Blackwell has no launch MSRP recorded.

FAQ

Q: Which GPU has higher raw FP32 compute?

A: The RTX PRO 4000 Blackwell delivers 36.83 TFLOPS FP32, while the Jetson Orin Nano Super delivers 2.089 TFLOPS, a 17.6x difference in favor of the RTX PRO 4000 Blackwell.

Q: How does memory bandwidth compare?

A: The RTX PRO 4000 Blackwell provides 672.0 GB/s from 24 GB GDDR7 on a 192-bit bus. The Jetson Orin Nano Super provides 102.4 GB/s from 8 GB LPDDR5 on a 128-bit bus.

Q: Which product supports ray tracing hardware?

A: Only the RTX PRO 4000 Blackwell lists 70 ray tracing cores. The Jetson Orin Nano Super records no RT core count.

Q: What are the power requirements for each?

A: The Jetson Orin Nano Super has a 25 W TDP and no power connector. The RTX PRO 4000 Blackwell has a 140 W TDP, uses one 16-pin connector, and suggests a 300 W PSU.

Q: Where does the RTX PRO 4000 Blackwell rank among its nearest rivals?

A: Its average benchmark score of 27,135 places it 1.1% behind the AMD Radeon RX 6700 XT, 1.1% behind the NVIDIA GeForce RTX 4070 Mobile, 1.6% behind the NVIDIA GeForce RTX 3090, and 1.7% ahead of the NVIDIA RTX A4000.

Q: What is the form factor difference?

A: The Jetson Orin Nano Super is an IGP measuring 70 mm by 45 mm. The RTX PRO 4000 Blackwell is a single-slot card measuring 241 mm by 111 mm by 20 mm.

Where Each One Wins

The Jetson Orin Nano Super wins in scenarios defined by physical constraints and power efficiency. Its 25 W TDP allows operation in compact embedded systems where the RTX PRO 4000 Blackwell's 140 W draw would be impractical. The 70 mm by 45 mm module footprint fits into portable devices and edge hardware, while the RTX PRO 4000 Blackwell requires a full 241 mm by 111 mm by 20 mm expansion slot. The Jetson's PCIe 4.0 x4 interface suits low-bandwidth embedded interconnects, and its "Portable Device Dependent" display outputs indicate flexibility for custom hardware designs. The 249 USD launch MSRP positions it as a low-cost compute module, though the analysis here does not weigh affordability. Its 50th percentile ranking and 102.4 GB/s bandwidth are modest, but for tasks like inference at the edge, sensor fusion, or robotics control, the recorded data shows a product designed for minimal energy and space, not maximum throughput.

The RTX PRO 4000 Blackwell wins in every performance category where numbers exist. Its 36.83 TFLOPS FP32 and FP16 (1:1) throughput, 672.0 GB/s memory bandwidth, and 70 RT cores make it suited for professional rendering, simulation, and compute workloads. The 24 GB GDDR7 frame buffer supports large datasets and high-resolution textures. The 4x DisplayPort 2.1b outputs drive multi-monitor professional setups. The 72nd percentile ranking among all GPUs, combined with a 1.7% lead over the RTX A4000 and a 1.1% gap to the RX 6700 XT and RTX 4070 Mobile, places it in a competitive workstation tier. Its 2055 MHz boost clock and 575.4 GTexel/s texture rate indicate sustained high-frequency operation. The PCIe 5.0 x16 interface provides ample host bandwidth for data transfer. For users with a desktop workstation, a 300 W PSU, and a need for ray-traced visuals or GPU compute, the data points exclusively to the RTX PRO 4000 Blackwell.

The split is clean: the Jetson Orin Nano Super covers deployment environments where power and size are the limiting factors, and the RTX PRO 4000 Blackwell covers environments where performance is the only metric that matters. The absence of benchmark scores for the Jetson means no direct performance comparison is possible, but the architectural figures alone establish that the RTX PRO 4000 Blackwell is the superior compute device by an order of magnitude across FP32, FP16, pixel rate, texture rate, and memory bandwidth.

DETAILED SPECIFICATIONS

SPECIFICATION
Jetson Orin Nano Super
RTX PRO 4000 Blackwell
Core Specs
Shading Units
1,024
8,960 +775.0%
Shaders
1,024
8,960 +775.0%
TMUs
32
280 +775.0%
ROPs
16
96 +500.0%
SM Count
8
70 +775.0%
Clocks
Base Clock
—
1230 MHz
Boost Clock
—
2055 MHz
GPU Clock
1020 MHz
—
Memory Clock
800 MHz 6.4 Gbps effective
1750 MHz 28 Gbps effective
Memory
Memory Size
8 GB
24 GB
VRAM (MB)
8,192
24,576 +200.0%
Memory Type
LPDDR5
GDDR7
Memory Bus
128 bit
192 bit
Bandwidth
102.4 GB/s
672.0 GB/s
Cache
L1 Cache
128 KB (per SM)
128 KB (per SM)
L2 Cache
2 MB
48 MB
Performance
Pixel Rate
16.32 GPixel/s
197.3 GPixel/s
Texture Rate
32.64 GTexel/s
575.4 GTexel/s
FP32 (TFLOPS)
2.089 TFLOPS
36.83 TFLOPS
FP64 (TFLOPS)
—
575.4 GFLOPS (1:64)
FP16 (TFLOPS)
4.178 TFLOPS (2:1)
36.83 TFLOPS (1:1)
AI/RT
RT Cores
—
70
Tensor Cores
32
280 +775.0%
Power
TDP
25 W
140 W
TDP (W)
25
140 +460.0%
Suggested PSU
—
300 W
Power Connectors
—
1x 16-pin
Architecture
Architecture
Ampere
Blackwell 2.0
GPU Name
GA10B
GB203
Generation
Tegra (Ampere)
Blackwell PRO W (x000)
Process Size
8 nm
5 nm
Transistors
unknown
45,600 million
Die Size
200 mm²
378 mm²
Foundry
Samsung
TSMC
Density
—
120.6M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
8.7
12.0
Shader Model
6.8
6.9
Physical
Slot Width
IGP
Single-slot
Length
70 mm 2.8 inches
241 mm 9.5 inches
Height
45 mm 1.8 inches
111 mm 4.4 inches
Outputs
Portable Device Dependent
4x DisplayPort 2.1b
Bus Interface
PCIe 4.0 x4
PCIe 5.0 x16
Other
Launch Price
249 USD
—
Production
Active
Active
Predecessor
—
Workstation Ada
View Jetson Orin Nano Super Details View RTX PRO 4000 Blackwell Details