NVIDIA GeForce RTX 5090 D vs NVIDIA N1X 48SM Comparison

The Verdict

The recorded database positions these two NVIDIA parts at opposite extremes of the product spectrum. The GeForce RTX 5090 D is a discrete, actively cooled, high-power add-in board aimed at maximum raster and ray tracing throughput. The N1X 48SM is an integrated graphics processor (IGP) with a massive unified memory pool, designed for a different class of system entirely. The data shows the RTX 5090 D delivers an average benchmark score of 77,712 across ten tests, while the N1X 48SM has no recorded benchmark scores and an average of 0. The RTX 5090 D sits at the 92nd percentile of all GPUs, whereas the N1X 48SM sits at the 50th percentile with no measured performance data. The verdict is straightforward: the RTX 5090 D is for users who need a discrete GPU with proven performance, while the N1X 48SM is a platform-level integration whose capabilities remain unquantified in this database.

Architecture Differences

Both chips share the Blackwell 2.0 architecture and are fabricated on a 5 nm process at TSMC, but the similarity ends there. The RTX 5090 D uses the GB202 chip with a die size of 750 mm² and 92,200 million transistors, resulting in a transistor density of 122.9M per mm². The N1X 48SM uses the GB20B chip with a die size of 382 mm², nearly half the area, and its transistor count is listed as unknown. The RTX 5090 D carries 21,760 shading units, 680 texture mapping units, 176 ROPs, 170 ray tracing cores, and 680 tensor cores. The N1X 48SM has 6,144 shading units, 384 TMUs, 48 ROPs, 48 RT cores, and 192 tensor cores. The core count difference is substantial: the RTX 5090 D has 3.5 times the shading units, 1.8 times the TMUs, 3.7 times the ROPs, and 3.5 times the RT cores. Clock speeds also diverge sharply. The RTX 5090 D runs at a base of 2017 MHz and a boost of 2407 MHz, while the N1X 48SM runs at 741 MHz base and 2346 MHz boost. The memory subsystem is a major architectural split. The RTX 5090 D uses 32 GB of GDDR7 on a 512-bit bus with 1.79 TB/s bandwidth, while the N1X 48SM uses 128 GB of LPDDR5X on a 256-bit bus with 273.2 GB/s bandwidth. The N1X 48SM has four times the capacity but only 15% of the bandwidth. The N1X 48SM is classified as an IGP with no power connectors, while the RTX 5090 D is a dual-slot card with a 575 W TDP and a single 16-pin connector. The N1X 48SM lists its API support as N/A for DirectX, OpenGL, and Vulkan, whereas the RTX 5090 D supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The N1X 48SM has a single HDMI output, while the RTX 5090 D offers 1x HDMI 2.1b and 3x DisplayPort 2.1b.

Head-to-Head Benchmarks

The head-to-head benchmark comparison table is empty, and the wins count for both parts is zero. The RTX 5090 D has a full suite of ten recorded benchmark scores, while the N1X 48SM has none. The RTX 5090 D's average benchmark score of 77,712 places it at the 92nd percentile of all GPUs. Its nearest rivals in the database are all other NVIDIA or AMD parts: the AMD Radeon RX 6650M XT with an average score of 76,904 (1.1% behind), the AMD Radeon RX 6850M XT with 78,940 (1.6% ahead), the NVIDIA Tesla P100 PCIe 12 GB with 79,396 (2.1% ahead), and the NVIDIA Tesla P100 PCIe 16 GB with 79,605 (2.4% ahead). The RTX 5090 D's individual scores show a wide spread across test types. In 3DMark Steel Nomad DX12 it scores 14,326. In Geekbench OpenCL it scores 310,674, and in Geekbench Vulkan it scores 376,915. PassMark tests show 231 in DirectX 10, 371 in DirectX 11, 219 in DirectX 12, 434 in DirectX 9, 1,487 in G2D, 44,065 in G3D, and 28,396 in GPU compute. The N1X 48SM has no comparable measurements, so no direct numerical comparison is possible from the recorded data. The N1X 48SM's percentile of 50 is a placeholder derived from its zero average score, not from actual performance results.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The RTX 5090 D has an average benchmark score of 77,712, while the N1X 48SM has an average benchmark score of 0 with no recorded benchmarks.

Q: What is the memory capacity difference?

A: The RTX 5090 D has 32 GB of GDDR7, while the N1X 48SM has 128 GB of LPDDR5X. The N1X 48SM has four times the capacity.

Q: How do the memory bandwidths compare?

A: The RTX 5090 D delivers 1.79 TB/s over a 512-bit bus, while the N1X 48SM delivers 273.2 GB/s over a 256-bit bus. The RTX 5090 D has roughly 6.5 times the bandwidth.

Q: Are the architectures the same?

A: Yes, both use the Blackwell 2.0 architecture and are built on a 5 nm process at TSMC. However, they use different chips: GB202 for the RTX 5090 D and GB20B for the N1X 48SM.

Q: What is the form factor difference?

A: The RTX 5090 D is a dual-slot discrete card measuring 304 mm by 137 mm by 48 mm, with a 575 W TDP and a 1x 16-pin power connector. The N1X 48SM is an IGP with no power connectors and no listed dimensions.

Q: What API support does each GPU offer?

A: The RTX 5090 D supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The N1X 48SM lists N/A for all three APIs.

Where Each One Wins

The RTX 5090 D wins in every measurable performance category because it is the only one with recorded data. Its FP32 compute is 104.8 TFLOPS, its pixel rate is 423.6 GPixel/s, and its texture rate is 1,636.8 GTexel/s. The N1X 48SM delivers 28.83 TFLOPS FP32, 112.6 GPixel/s, and 900.9 GTexel/s. The RTX 5090 D is 3.6 times higher in FP32 throughput, 3.8 times higher in pixel rate, and 1.8 times higher in texture rate. The RTX 5090 D also has a higher boost clock at 2407 MHz versus 2346 MHz, and a much higher base clock at 2017 MHz versus 741 MHz. The N1X 48SM's only advantage is memory capacity: 128 GB versus 32 GB. That capacity could be relevant for large datasets, but the N1X 48SM's bandwidth is far lower, and its API support is listed as N/A, which limits its applicability in standard graphics workloads. The RTX 5090 D's 92nd percentile ranking versus the N1X 48SM's 50th percentile underscores the gulf in measured performance. The N1X 48SM has no rivals listed in the database, while the RTX 5090 D sits within 2.4% of four different competitors, showing that it is tightly grouped with high-end parts from both NVIDIA and AMD.

Specification Differences

The two GPUs differ in nearly every specification field. The RTX 5090 D uses the GB202 chip; the N1X 48SM uses the GB20B chip. Die size is 750 mm² for the RTX 5090 D and 382 mm² for the N1X 48SM. Transistor count is 92,200 million for the RTX 5090 D and unknown for the N1X 48SM. Transistor density is 122.9M per mm² for the RTX 5090 D and not listed for the N1X 48SM. Base clock is 2017 MHz versus 741 MHz. Boost clock is 2407 MHz versus 2346 MHz. Memory clock is 1750 MHz (28 Gbps effective) versus 1067 MHz (8.5 Gbps effective). Memory size is 32 GB GDDR7 versus 128 GB LPDDR5X. Bus width is 512 bit versus 256 bit. Bandwidth is 1.79 TB/s versus 273.2 GB/s. Shading units are 21,760 versus 6,144. TMUs are 680 versus 384. ROPs are 176 versus 48. RT cores are 170 versus 48. Tensor cores are 680 versus 192. Pixel rate is 423.6 GPixel/s versus 112.6 GPixel/s. Texture rate is 1,636.8 GTexel/s versus 900.9 GTexel/s. FP32 is 104.8 TFLOPS versus 28.83 TFLOPS. FP16 is 104.8 TFLOPS (1:1) versus 28.83 TFLOPS (1:1). TDP is 575 W versus unknown. Slot width is dual-slot versus IGP. Power connectors are 1x 16-pin versus none. Suggested PSU is 950 W versus not listed. Display outputs are 1x HDMI 2.1b plus 3x DisplayPort 2.1b versus 1x HDMI. API support is DirectX 12 Ultimate, OpenGL 4.6, Vulkan 1.4 versus N/A for all three. The RTX 5090 D has dimensions of 304 mm by 137 mm by 48 mm; the N1X 48SM has no listed dimensions. Release dates differ: 2025-01-29 for the RTX 5090 D and 2026-05-31 for the N1X 48SM. The RTX 5090 D has a launch MSRP of 2,299 USD; the N1X 48SM has no launch MSRP listed.