NVIDIA GeForce RTX 4080 SUPER vs NVIDIA GeForce RTX 5090 Mobile Comparison

Head-to-Head Benchmarks

The benchmark data is decisively one-sided: the NVIDIA GeForce RTX 4080 SUPER wins 9 of 10 head-to-head tests, with the single exception being a narrow passmark DirectX 12 result. The average benchmark score tells the same story, the RTX 4080 SUPER posts 54209 points against 45152 for the RTX 5090 Mobile, a gap of roughly 20%.

The largest margin comes in compute workloads. In passmark GPU compute, the RTX 4080 SUPER scores 19822 versus 13401 for the RTX 5090 Mobile, a 47.9% advantage. This is the clearest separation in the entire comparison, and it reflects a fundamental difference in how these two GPUs are built and powered.

Vulkan performance shows another notable gap. The RTX 4080 SUPER reaches 260075 in Geekbench Vulkan, while the RTX 5090 Mobile manages 198405, a 31.1% lead. OpenCL results are closer but still favor the desktop card: 219065 versus 201834, an 8.5% difference.

In DirectX 9, the RTX 4080 SUPER scores 381 against 324, a 17.6% win. DirectX 11 shows 301 versus 269, an 11.9% margin. The 3DMark Steel Nomad DX12 test, a modern workload, gives the RTX 4080 SUPER 6600 points against 5871, a 12.4% lead. Passmark G3D follows with 34245 versus 30034, a 14% advantage.

The RTX 5090 Mobile's only victory is in passmark DirectX 12, where it scores 138 against 134, a 2.9% edge. This is a small win in a single legacy test, and it does not offset the pattern elsewhere.

The G2D test (2D graphics) also favors the RTX 4080 SUPER: 1270 versus 1057, a 20.2% margin. The DirectX 10 test is the closest overall, with 193 versus 183, a 5.5% lead for the desktop part.

The percentile data confirms the hierarchy. The RTX 4080 SUPER sits at the 86th percentile among all GPUs, while the RTX 5090 Mobile sits at the 84th. Both are high performers, but the desktop card ranks above the mobile part in the database's overall distribution.

When placed against their nearest rivals, the two cards occupy different tiers. The RTX 4080 SUPER's closest competitor is the RTX 4080, which averages 54247, a negligible 0.1% difference. The RTX 5090 Mobile's nearest rival is the AMD Radeon Pro 5500 XT at 45384, only 0.5% behind, and it is 0.8% ahead of the RTX 4070 Ti. The mobile card performs at the level of desktop GPUs from one generation earlier, while the RTX 4080 SUPER competes with the top of its own generation.

Architecture Differences

Both GPUs are built on a 5 nm process at TSMC, but the underlying designs diverge significantly. The RTX 4080 SUPER uses the AD103 chip from the Ada Lovelace architecture, while the RTX 5090 Mobile uses the GB203 chip from the Blackwell 2.0 architecture. Transistor counts are nearly identical: 45,900 million for the desktop card and 45,600 million for the mobile card. Die sizes are also close, 379 mm² versus 378 mm², and transistor density is within 0.5M per mm² (121.1M versus 120.6M).

Clock speeds reveal the core difference. The RTX 4080 SUPER runs at a base clock of 2295 MHz and boosts to 2550 MHz. The RTX 5090 Mobile is far lower: 990 MHz base and 1515 MHz boost. This explains the performance gap despite similar silicon. The desktop part is allowed to draw up to 320 W, while the mobile part is capped at 95 W, a power envelope that forces much lower clocks.

The memory subsystems differ in type and bandwidth. The RTX 4080 SUPER uses 16 GB of GDDR6X on a 256 bit bus, delivering 736.3 GB/s at 23 Gbps effective. The RTX 5090 Mobile uses 24 GB of GDDR7 on the same 256 bit bus, but reaches 896.0 GB/s at 28 Gbps effective. The mobile card has more capacity and higher bandwidth, yet this does not translate into higher frame rates in the recorded tests.

Compute resources are similar on paper. The RTX 4080 SUPER has 10240 shading units, 320 TMUs, 112 ROPs, 80 RT cores, and 320 tensor cores. The RTX 5090 Mobile has 10496 shading units, 328 TMUs, 112 ROPs, 82 RT cores, and 328 tensor cores. The mobile part has slightly more of everything except ROPs, which are equal. Despite this, the desktop card's higher clocks produce far higher throughput: 52.22 TFLOPS FP32 versus 31.80 TFLOPS, and 816.0 GTexel/s versus 496.9 GTexel/s. Pixel rate also favors the desktop card: 285.6 GPixel/s versus 169.7 GPixel/s.

The RTX 4080 SUPER is a triple-slot card with a 16-pin power connector and a suggested 700 W PSU. The RTX 5090 Mobile is an IGP (integrated graphics processor) with no power connector, designed for laptops. The desktop card uses PCIe 4.0 x16, while the mobile part uses PCIe 5.0 x16. Display outputs also differ: the RTX 4080 SUPER has 1x HDMI 2.1 and 3x DisplayPort 1.4a, while the RTX 5090 Mobile is described as "Portable Device Dependent." Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Production status separates them further. The RTX 4080 SUPER is end-of-life with a release date of January 30, 2024, and its predecessor is GeForce 30 with a successor in GeForce 50. The RTX 5090 Mobile is active, released March 26, 2025, and its predecessor is GeForce 40 Mobile. The launch MSRP of the RTX 4080 SUPER is 999 USD, while the RTX 5090 Mobile has no recorded launch MSRP.

The Verdict

The data is unambiguous: the NVIDIA GeForce RTX 4080 SUPER is the faster GPU in nearly every recorded workload. It wins 9 of 10 head-to-head tests, holds a 20% lead in average benchmark score, and ranks two percentile points higher in the overall distribution. The largest margins are in compute (47.9%), Vulkan (31.1%), and G2D (20.2%), areas where the desktop card's higher clocks and 320 W power budget provide a decisive advantage.

The RTX 5090 Mobile is not a weak product. It sits at the 84th percentile, outperforms the RTX 4070 Ti by 0.8%, and nearly matches the AMD Radeon Pro 5500 XT. Its 24 GB of GDDR7 memory and 896.0 GB/s bandwidth exceed the RTX 4080 SUPER in both capacity and bandwidth. It also wins the only DirectX 12 legacy test, albeit by a slim 2.9% margin.

However, the mobile part cannot overcome its 95 W power limit. Its base clock of 990 MHz and boost of 1515 MHz are far below the desktop card's 2295 MHz and 2550 MHz. The result is lower FP32 throughput (31.80 TFLOPS versus 52.22 TFLOPS), lower texture rate (496.9 GTexel/s versus 816.0 GTexel/s), and lower pixel rate (169.7 GPixel/s versus 285.6 GPixel/s).

For users who need maximum performance in a desktop system, the RTX 4080 SUPER is the clear choice based on the recorded data. For users who need a mobile GPU with high memory capacity and bandwidth in a laptop form factor, the RTX 5090 Mobile is the only option in this comparison, and it delivers solid performance despite its power constraints. The choice is not about which is faster; it is about which form factor matches the use case.

FAQ

Q: Which GPU wins more benchmark tests?

A: The NVIDIA GeForce RTX 4080 SUPER wins 9 of 10 head-to-head tests. The RTX 5090 Mobile wins only the passmark DirectX 12 test, scoring 138 versus 134.

Q: What is the biggest performance gap between the two?

A: The largest gap is in passmark GPU compute, where the RTX 4080 SUPER scores 19822 against 13401, a 47.9% lead.

Q: Does the RTX 5090 Mobile have more memory?

A: Yes, the RTX 5090 Mobile has 24 GB of GDDR7 memory, while the RTX 4080 SUPER has 16 GB of GDDR6X. The mobile card also has higher bandwidth: 896.0 GB/s versus 736.3 GB/s.

Q: How do their average benchmark scores compare?

A: The RTX 4080 SUPER averages 54209 points, while the RTX 5090 Mobile averages 45152 points. This is approximately a 20% difference in favor of the desktop card.

Q: Are they built on the same process node?

A: Yes, both use a 5 nm process at TSMC. Transistor counts are nearly identical: 45,900 million for the RTX 4080 SUPER and 45,600 million for the RTX 5090 Mobile.

Q: What are the power consumption figures?

A: The RTX 4080 SUPER has a TDP of 320 W and requires a 16-pin power connector with a suggested 700 W PSU. The RTX 5090 Mobile has a TDP of 95 W and uses no power connector, as it is an IGP.

Where Each One Wins

The RTX 4080 SUPER wins in compute-heavy tasks. Its 47.9% lead in passmark GPU compute makes it the better choice for workloads that rely on raw FP32 throughput, such as rendering, simulation, or any general-purpose GPU compute. Its 31.1% lead in Vulkan also suggests an advantage in Vulkan-based games and applications.

The RTX 4080 SUPER dominates legacy DirectX workloads. It leads by 17.6% in DirectX 9, 11.9% in DirectX 11, and 5.5% in DirectX 10. The only exception is DirectX 12, where the RTX 5090 Mobile wins by 2.9% in the passmark test, though the RTX 4080 SUPER wins the 3DMark Steel Nomad DX12 test by 12.4%.

The RTX 5090 Mobile wins in memory capacity and bandwidth. With 24 GB of GDDR7 and 896.0 GB/s, it offers more headroom for large datasets, high-resolution textures, or AI models that exceed 16 GB. It also wins the passmark DirectX 12 test, which may indicate better optimization in that specific legacy workload.

For 2D tasks, the RTX 4080 SUPER leads by 20.2% in passmark G2D. For general 3D performance, the RTX 4080 SUPER leads by 14% in passmark G3D. The RTX 5090 Mobile's only realistic advantage in the recorded data is its form factor: it is an IGP with no power connector, suitable for laptops, while the RTX 4080 SUPER is a triple-slot desktop card.

Specification Differences

The two GPUs differ in nearly every major specification category. The RTX 4080 SUPER uses the AD103 chip from Ada Lovelace, while the RTX 5090 Mobile uses the GB203 chip from Blackwell 2.0. Both are 5 nm TSMC parts with similar transistor counts (45,900 million versus 45,600 million) and die sizes (379 mm² versus 378 mm²).

Clock speeds are the most dramatic difference. The RTX 4080 SUPER runs at 2295 MHz base and 2550 MHz boost. The RTX 5090 Mobile runs at 990 MHz base and 1515 MHz boost. Memory clocks also differ: 1438 MHz (23 Gbps effective) for the desktop card versus 1750 MHz (28 Gbps effective) for the mobile card.

Memory configurations diverge: 16 GB GDDR6X versus 24 GB GDDR7, both on a 256 bit bus, but with different bandwidth (736.3 GB/s versus 896.0 GB/s). The RTX 4080 SUPER has 10240 shading units, 320 TMUs, 112 ROPs, 80 RT cores, and 320 tensor cores. The RTX 5090 Mobile has 10496 shading units, 328 TMUs, 112 ROPs, 82 RT cores, and 328 tensor cores.

Rates differ substantially. The RTX 4080 SUPER delivers 285.6 GPixel/s, 816.0 GTexel/s, and 52.22 TFLOPS FP32. The RTX 5090 Mobile delivers 169.7 GPixel/s, 496.9 GTexel/s, and 31.80 TFLOPS FP32. Power consumption is 320 W versus 95 W. The desktop card is triple-slot with a 16-pin connector and a suggested 700 W PSU; the mobile part is an IGP with no connector and no suggested PSU.

Bus interfaces differ: PCIe 4.0 x16 for the RTX 4080 SUPER versus PCIe 5.0 x16 for the RTX 5090 Mobile. Display outputs are 1x HDMI 2.1 and 3x DisplayPort 1.4a for the desktop card, while the mobile card is "Portable Device Dependent." Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The RTX 4080 SUPER is end-of-life with a launch MSRP of 999 USD; the RTX 5090 Mobile is active with no launch MSRP recorded.