NVIDIA GeForce RTX 5090 SE vs NVIDIA Jetson T5000 Comparison

The Verdict

The database shows two NVIDIA designs built on the same 5 nm TSMC process but aimed at entirely different workloads. The GeForce RTX 5090 SE is a high-throughput graphics card for desktop rendering and gaming, while the Jetson T5000 is a compact embedded server module with no display outputs. The recorded specifications indicate that the RTX 5090 SE delivers roughly 8.3 times the FP32 compute of the Jetson T5000 (66.94 TFLOPS versus 8.064 TFLOPS), along with a pixel rate of 380.3 GPixel/s versus 50.40 GPixel/s. The Jetson T5000 counters with 128 GB of LPDDR5X memory, a 5.3 times capacity advantage over the RTX 5090 SE's 24 GB, and a 120 W TDP that is 380 W lower than the RTX 5090 SE's 500 W. Users needing maximum rasterization throughput, ray tracing, or display connectivity should select the RTX 5090 SE. Users prioritizing memory capacity for large model inference or constrained power envelopes should select the Jetson T5000. The RTX 5090 SE also carries a lower launch MSRP of 1,499 USD versus 2,999 USD for the Jetson T5000.

Architecture Differences

The RTX 5090 SE uses the GB202 chip with Blackwell 2.0 architecture, while the Jetson T5000 uses the GB10B chip with the base Blackwell architecture. Both are fabricated on a 5 nm process at TSMC, but the dies differ substantially: the RTX 5090 SE measures 750 mm² with 92,200 million transistors and a density of 122.9M per mm², whereas the Jetson T5000 measures 391 mm² with transistor count listed as unknown. The RTX 5090 SE belongs to the GeForce 50 generation, succeeding GeForce 40 and preceding GeForce 60. The Jetson T5000 belongs to the Server Blackwell (Bxx) generation, succeeding Server Hopper and preceding Server Rubin.

The compute resources diverge sharply. The RTX 5090 SE packs 14,080 shading units, 440 TMUs, 160 ROPs, 110 RT cores, and 440 tensor cores. The Jetson T5000 has 2,560 shading units, 80 TMUs, 32 ROPs, 20 RT cores, and 96 tensor cores. Both implement FP16 at a 1:1 ratio with FP32, meaning each delivers the same TFLOPS for both precision formats. The RTX 5090 SE supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The Jetson T5000 lists all APIs as N/A, consistent with its server-oriented design that has no display outputs.

Clock speeds also differ. The RTX 5090 SE has a base clock of 1740 MHz and a boost clock of 2377 MHz, while the Jetson T5000 runs at 1386 MHz base and 1575 MHz boost. Memory clocks follow the same pattern: the RTX 5090 SE runs at 1750 MHz with 28 Gbps effective transfer, while the Jetson T5000 runs at 1067 MHz with 8.5 Gbps effective.

Head-to-Head Benchmarks

No direct benchmark scores exist in the database for either device, so the comparison relies on recorded specification-derived rates. The most decisive advantage for the RTX 5090 SE is compute throughput. Its FP32 figure of 66.94 TFLOPS is 8.3 times the Jetson T5000's 8.064 TFLOPS, a gap that reflects the 5.5 times difference in shading units (14,080 versus 2,560). The texture rate follows a similar pattern: 1,045.9 GTexel/s versus 126.0 GTexel/s, an 8.3 times margin driven by the 440 TMUs versus 80 TMUs.

Pixel throughput shows an even larger relative difference. The RTX 5090 SE delivers 380.3 GPixel/s against 50.40 GPixel/s for the Jetson T5000, a 7.5 times gap. This stems from the 160 ROPs versus 32 ROPs on the Jetson T5000. Memory bandwidth favors the RTX 5090 SE by a factor of 4.9: 1.34 TB/s versus 273.2 GB/s. The RTX 5090 SE uses a 384-bit bus with GDDR7, while the Jetson T5000 uses a 256-bit bus with LPDDR5X.

The Jetson T5000 wins on memory capacity. Its 128 GB is 5.3 times the RTX 5090 SE's 24 GB, a decisive advantage for workloads that must hold large datasets or model weights entirely in local memory. The Jetson T5000 also wins on power efficiency as recorded: its 120 W TDP delivers 8.064 TFLOPS, yielding 0.0672 TFLOPS per watt, while the RTX 5090 SE's 500 W TDP delivers 66.94 TFLOPS, yielding 0.1339 TFLOPS per watt. The RTX 5090 SE is approximately twice as efficient per watt despite drawing 380 W more absolute power. The Jetson T5000 requires a 300 W suggested PSU versus 900 W for the RTX 5090 SE, and it uses no power connectors at all, whereas the RTX 5090 SE needs a 16-pin connector.

Specification Differences

The two devices differ in every major specification category recorded. The RTX 5090 SE has a 1740 MHz base clock and 2377 MHz boost, while the Jetson T5000 has 1386 MHz base and 1575 MHz boost. Memory capacity is 24 GB GDDR7 for the RTX 5090 SE versus 128 GB LPDDR5X for the Jetson T5000. Bus width is 384 bit versus 256 bit. Bandwidth is 1.34 TB/s versus 273.2 GB/s. Shading units are 14,080 versus 2,560. TMUs are 440 versus 80. ROPs are 160 versus 32. RT cores are 110 versus 20. Tensor cores are 440 versus 96. Pixel rate is 380.3 GPixel/s versus 50.40 GPixel/s. Texture rate is 1,045.9 GTexel/s versus 126.0 GTexel/s. FP32 is 66.94 TFLOPS versus 8.064 TFLOPS. FP16 is identical to each device's FP32 at 1:1.

TDP is 500 W versus 120 W. Slot width is dual-slot versus IGP. Power connectors are 1x 16-pin versus none. Suggested PSU is 900 W versus 300 W. Bus interface is PCIe 5.0 x16 versus PCIe 5.0 x8. Display outputs are 1x HDMI 2.1b and 3x DisplayPort 2.1b versus no outputs. Dimensions are 267 mm length, 111 mm height, 40 mm width for the RTX 5090 SE, versus 87 mm length, 100 mm height, 15 mm width for the Jetson T5000. The RTX 5090 SE release date is 2025-12-31, while the Jetson T5000 release date is 2025-08-26. Die size is 750 mm² versus 391 mm². Transistor count is 92,200 million versus unknown. Transistor density is 122.9M per mm² versus null. The RTX 5090 SE lists DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4 support; the Jetson T5000 lists N/A for all three. Launch MSRP is 1,499 USD for the RTX 5090 SE and 2,999 USD for the Jetson T5000.

FAQ

Q: Which GPU has higher raw compute performance?

A: The RTX 5090 SE delivers 66.94 TFLOPS FP32 and FP16, which is 8.3 times the Jetson T5000's 8.064 TFLOPS in both precisions.

Q: Which GPU has more memory?

A: The Jetson T5000 has 128 GB of LPDDR5X, which is 5.3 times the RTX 5090 SE's 24 GB of GDDR7.

Q: What is the power consumption difference?

A: The RTX 5090 SE has a 500 W TDP and requires a 900 W suggested PSU with a 16-pin connector. The Jetson T5000 has a 120 W TDP, requires a 300 W suggested PSU, and uses no power connectors.

Q: Can the Jetson T5000 output video to a display?

A: No. The Jetson T5000 lists no display outputs and has N/A for DirectX, OpenGL, and Vulkan support. The RTX 5090 SE has 1x HDMI 2.1b and 3x DisplayPort 2.1b outputs.

Q: How do the memory bandwidths compare?

A: The RTX 5090 SE has 1.34 TB/s bandwidth on a 384-bit bus with GDDR7. The Jetson T5000 has 273.2 GB/s bandwidth on a 256-bit bus with LPDDR5X, a 4.9 times difference.

Q: Which GPU has more tensor cores for AI workloads?

A: The RTX 5090 SE has 440 tensor cores, while the Jetson T5000 has 96 tensor cores. The RTX 5090 SE also has 110 RT cores versus 20 on the Jetson T5000.