NVIDIA GeForce RTX 5090 Mobile vs NVIDIA GeForce RTX 5090 SE Comparison

Head-to-Head Benchmarks

The database contains no shared benchmark results between the NVIDIA GeForce RTX 5090 Mobile and the NVIDIA GeForce RTX 5090 SE. The RTX 5090 Mobile has ten recorded benchmark scores, while the RTX 5090 SE has zero recorded scores in the database. The head-to-head comparison field is empty, and the win counters for both products stand at zero. Direct score comparisons are therefore impossible from the recorded data.

The RTX 5090 Mobile's available measurements establish its performance tier independently. Its 3DMark Steel Nomad DX12 score is 5871. Geekbench OpenCL returns 201834, and Geekbench Vulkan returns 198405. Passmark G3D shows 30034, with Passmark GPU Compute at 13401. The average benchmark score across all recorded tests is 45152. The RTX 5090 SE, by contrast, has an average benchmark score of 0 in the database, indicating no completed test runs have been logged.

The RTX 5090 Mobile sits at the 84th percentile of all GPUs in the database. Its nearest rivals include the AMD Radeon Pro 5500 XT with an average score of 45384 (0.5% higher), the NVIDIA GeForce RTX 4070 Ti at 44795 (0.8% lower), the Intel Arc A730M at 45592 (1% higher), and the NVIDIA RTX 5880 Ada Generation at 45972 (1.8% higher). These margins are narrow, placing the mobile part in a tight competitive cluster. The RTX 5090 SE is listed at the 50th percentile with no rival data, which reflects its absence of logged benchmarks rather than measured performance.

Without head-to-head scores, the specification sheet provides the only quantitative basis for comparing these two parts. The RTX 5090 SE carries substantially higher rated resources, but no benchmark evidence confirms how that translates into real-world results. The RTX 5090 Mobile's recorded scores show a capable performer within its mobile power envelope, yet the SE's potential remains unquantified by the database.

Architecture Differences

Both GPUs share the Blackwell 2.0 architecture, the GeForce 50-series branding, a 5 nm TSMC process node, and identical API support for DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The fundamental divergence lies in the silicon. The RTX 5090 Mobile uses the GB203 chip, while the RTX 5090 SE uses the GB202 chip.

Transistor counts differ sharply. The GB203 in the mobile part contains 45,600 million transistors on a 378 mm² die, yielding a density of 120.6 million transistors per square millimeter. The GB202 in the SE contains 92,200 million transistors on a 750 mm² die, with a density of 122.9 million per square millimeter. The SE's die is nearly double the mobile chip's area, and its transistor count is roughly double as well, though the density figures are close.

Core configurations scale accordingly. The RTX 5090 Mobile has 10496 shading units, 328 texture mapping units, 112 raster output units, 82 ray tracing cores, and 328 tensor cores. The RTX 5090 SE has 14080 shading units, 440 TMUs, 160 ROPs, 110 RT cores, and 440 tensor cores. The SE leads in every core category: 33% more shading units, 34% more TMUs, 43% more ROPs, 34% more RT cores, and 34% more tensor cores.

Clock speeds also differ substantially. The mobile part runs at a base clock of 990 MHz and a boost clock of 1515 MHz. The SE runs at 1740 MHz base and 2377 MHz boost. Both use the same memory clock of 1750 MHz with 28 Gbps effective speed, and both employ GDDR7 memory with 24 GB capacity. Memory bus width differs: 256 bit for the mobile part versus 384 bit for the SE, which drives the bandwidth gap from 896.0 GB/s to 1.34 TB/s.

The compute throughput reflects both core counts and clocks. The RTX 5090 Mobile delivers 31.80 TFLOPS for both FP32 and FP16 (1:1 ratio), with a pixel rate of 169.7 GPixel/s and a texture rate of 496.9 GTexel/s. The RTX 5090 SE delivers 66.94 TFLOPS for both FP32 and FP16, with a pixel rate of 380.3 GPixel/s and a texture rate of 1,045.9 GTexel/s. The SE more than doubles the mobile part's floating-point throughput and pixel fill rate.

Power and physical design differ as much as the silicon. The mobile GPU has a TDP of 95 W, an IGP slot width, no power connectors, and display outputs described as portable device dependent. The SE has a TDP of 500 W, a dual-slot width, a single 16-pin power connector, a suggested PSU of 900 W, and fixed display outputs of 1x HDMI 2.1b and 3x DisplayPort 2.1b. The SE measures 267 mm in length, 111 mm in height, and 40 mm in width. The mobile part has no recorded dimensions.

Where Each One Wins

The RTX 5090 Mobile wins in portability and integration. Its 95 W TDP permits IGP-class packaging with no external power connectors, making it suitable for laptops and compact systems where the SE's 500 W TDP, dual-slot cooler, 16-pin connector, and 900 W suggested PSU cannot apply. The mobile part also has a recorded benchmark history, with an average score of 45152 and ten individual test results, which allows performance assessment against known rivals. The SE has no recorded benchmarks, so its measured performance cannot be compared.

The RTX 5090 SE wins on raw specification strength across every compute metric. Its shading unit count, TMU count, ROP count, RT core count, and tensor core count all exceed the mobile part by roughly one-third or more. Its FP32 throughput of 66.94 TFLOPS is more than double the mobile's 31.80 TFLOPS. Its pixel rate of 380.3 GPixel/s is 2.24 times the mobile's 169.7 GPixel/s. Its texture rate of 1,045.9 GTexel/s is 2.11 times the mobile's 496.9 GTexel/s. Its memory bandwidth of 1.34 TB/s is 1.5 times the mobile's 896.0 GB/s.

Clock speed advantage belongs to the SE as well. The SE's base clock of 1740 MHz is 76% higher than the mobile's 990 MHz, and its boost clock of 2377 MHz is 57% higher than the mobile's 1515 MHz. These clock differences compound the core count advantages, producing the large throughput gap.

For workloads that fit within the mobile power envelope, the RTX 5090 Mobile offers the only measured evidence of performance. Its 3DMark Steel Nomad score of 5871 and Passmark G3D score of 30034 place it in the 84th percentile of all GPUs, with rivals within roughly 2% in either direction. For workloads that require the SE's full specification, the database holds no recorded confirmation of its output, only the hardware's rated capabilities.

Specification Differences

The two GPUs differ in chip, transistor count, die size, clock speeds, memory bus width, bandwidth, core counts, throughput rates, TDP, physical dimensions, power connectors, display outputs, release date, and predecessor. They share the same architecture, process node, foundry, memory type, memory size, memory clock, API support, bus interface, and production status.

| Field | RTX 5090 Mobile | RTX 5090 SE |

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

| Chip | GB203 | GB202 |

| Transistors | 45,600 million | 92,200 million |

| Die size | 378 mm² | 750 mm² |

| Transistor density | 120.6M / mm² | 122.9M / mm² |

| Base clock | 990 MHz | 1740 MHz |

| Boost clock | 1515 MHz | 2377 MHz |

| Memory bus width | 256 bit | 384 bit |

| Memory bandwidth | 896.0 GB/s | 1.34 TB/s |

| Shading units | 10496 | 14080 |

| TMUs | 328 | 440 |

| ROPs | 112 | 160 |

| RT cores | 82 | 110 |

| Tensor cores | 328 | 440 |

| Pixel rate | 169.7 GPixel/s | 380.3 GPixel/s |

| Texture rate | 496.9 GTexel/s | 1,045.9 GTexel/s |

| FP32 / FP16 | 31.80 TFLOPS | 66.94 TFLOPS |

| TDP | 95 W | 500 W |

| Slot width | IGP | Dual-slot |

| Power connectors | None | 1x 16-pin |

| Suggested PSU | None | 900 W |

| Display outputs | Portable Device Dependent | 1x HDMI 2.1b, 3x DisplayPort 2.1b |

| Dimensions | None recorded | 267 mm, 111 mm, 40 mm |

| Release date | 2025-03-26 | 2025-12-31 |

| Predecessor | GeForce 40 Mobile | GeForce 40 |

| Successor | None | GeForce 60 |

| Launch MSRP | None | 1,499 USD |

The transistor density difference is small (120.6M vs 122.9M per mm²), indicating similar manufacturing efficiency despite the large die size gap. The mobile part releases earlier in 2025, while the SE releases later that year. The SE has a successor listed, GeForce 60, while the mobile part does not. The SE's launch MSRP is 1,499 USD, stated once here as recorded.

FAQ

Q: Which GPU has more shading units?

A: The NVIDIA GeForce RTX 5090 SE has 14080 shading units, while the NVIDIA GeForce RTX 5090 Mobile has 10496.

Q: What is the memory bandwidth difference?

A: The RTX 5090 Mobile has 896.0 GB/s over a 256 bit bus, while the RTX 5090 SE has 1.34 TB/s over a 384 bit bus. Both use 24 GB of GDDR7 memory at 1750 MHz with 28 Gbps effective speed.

Q: How do the power requirements compare?

A: The RTX 5090 Mobile has a TDP of 95 W, an IGP slot width, and no power connectors. The RTX 5090 SE has a TDP of 500 W, a dual-slot width, one 16-pin power connector, and a suggested PSU of 900 W.

Q: Does the RTX 5090 Mobile have benchmark scores?

A: Yes, it has ten recorded scores including 3DMark Steel Nomad DX12 at 5871, Geekbench OpenCL at 201834, Geekbench Vulkan at 198405, Passmark G3D at 30034, and an average benchmark score of 45152. The RTX 5090 SE has no recorded benchmark scores.

Q: What is the FP32 throughput of each GPU?

A: The RTX 5090 Mobile delivers 31.80 TFLOPS for FP32 (and FP16 at a 1:1 ratio). The RTX 5090 SE delivers 66.94 TFLOPS for FP32 (and FP16 at a 1:1 ratio).

Q: Which GPU uses a larger die?

A: The RTX 5090 SE uses the GB202 chip with a 750 mm² die containing 92,200 million transistors. The RTX 5090 Mobile uses the GB203 chip with a 378 mm² die containing 45,600 million transistors. Both are built on a 5 nm TSMC process.