NVIDIA GeForce RTX 5080 vs NVIDIA GeForce RTX 5090 Mobile Comparison

FAQ

Q: What are the average benchmark scores for the NVIDIA GeForce RTX 5080 and the NVIDIA GeForce RTX 5090 Mobile?

A: The RTX 5080 has an average benchmark score of 56083, while the RTX 5090 Mobile averages 45152. The 5080 sits at the 87th percentile of all GPUs, and the 5090 Mobile sits at the 84th percentile.

Q: Which GPU wins in DirectX 12 performance in the recorded data?

A: The RTX 5080 wins in the 3DMark Steel Nomad DX12 test with a score of 8637 versus 5871 for the RTX 5090 Mobile, a 47.1% difference. In Passmark DirectX 12, the 5080 scores 151 versus 138, a 9.4% lead.

Q: How do the two compare in compute workloads?

A: The RTX 5080 leads Passmark GPU Compute with 21789 points versus 13401 for the RTX 5090 Mobile, a 62.6% advantage. In Geekbench OpenCL, the 5080 scores 235901 against 201834, a 16.9% lead.

Q: What are the memory configurations of each GPU?

A: The RTX 5080 has 16 GB of GDDR7 on a 256-bit bus with 960.0 GB/s bandwidth. The RTX 5090 Mobile has 24 GB of GDDR7 on a 256-bit bus with 896.0 GB/s bandwidth.

Q: Do both GPUs use the same chip and architecture?

A: Yes, both use the GB203 chip with Blackwell 2.0 architecture, built on a 5 nm process at TSMC, with 45,600 million transistors and a 378 mm² die size.

Q: Which GPU has a higher boost clock?

A: The RTX 5080 boosts to 2617 MHz, while the RTX 5090 Mobile boosts to 1515 MHz. The 5080 also has a higher base clock at 2295 MHz versus 990 MHz.

Where Each One Wins

The RTX 5080 wins in every recorded head-to-head benchmark, taking 10 out of 10 tests. Its largest margins appear in compute-heavy and modern API workloads. The 3DMark Steel Nomad DX12 test shows a 47.1% lead, and Passmark GPU Compute shows a 62.6% lead. These are the clearest indicators of where the desktop card dominates: sustained shader throughput and raw FP32 work.

The RTX 5090 Mobile does not win any benchmark, but its strongest relative performance comes in Passmark DirectX 12, where it trails by only 9.4%. This suggests that in legacy or lightly threaded DX12 titles, the mobile part is closer to the desktop card than in other workloads. The gap widens in older APIs: DirectX 10 shows a 13.7% difference, DirectX 11 a 20.4% difference, and DirectX 9 a 20.1% difference.

For users prioritizing frame rates in modern DX12 titles, the RTX 5080 is the clear choice. For those who need portability and can accept lower absolute scores, the RTX 5090 Mobile remains competitive in specific legacy scenarios, though still behind. The data shows no scenario where the mobile GPU outperforms the desktop card.

Architecture Differences

Both GPUs share the same GB203 chip, Blackwell 2.0 architecture, 5 nm TSMC process, 45,600 million transistors, and 378 mm² die size. The transistor density is identical at 120.6M per mm². This means the fundamental silicon is the same, but the configuration and power envelope differ substantially.

The RTX 5080 has 10752 shading units, 336 TMUs, 112 ROPs, 84 RT cores, and 336 tensor cores. The RTX 5090 Mobile has 10496 shading units, 328 TMUs, 112 ROPs, 82 RT cores, and 328 tensor cores. The desktop card carries slightly more of every compute resource, but the differences are small: 256 shading units, 8 TMUs, 2 RT cores, and 8 tensor cores.

Clock speeds create the largest architectural divergence. The RTX 5080 runs at 2295 MHz base and 2617 MHz boost, while the RTX 5090 Mobile runs at 990 MHz base and 1515 MHz boost. This nearly 1100 MHz boost clock gap drives the performance difference more than the modest core count delta.

Power delivery also differs. The RTX 5080 has a 360 W TDP and requires a 1x 16-pin power connector with a suggested 750 W PSU. The RTX 5090 Mobile has a 95 W TDP, uses no external power connectors, and is an IGP (integrated graphics processor) form factor. The 265 W TDP difference explains the clock disparity: the desktop card has far more thermal and electrical headroom.

Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, and both use PCIe 5.0 x16. Display outputs differ: the RTX 5080 offers 1x HDMI 2.1b and 3x DisplayPort 2.1b, while the RTX 5090 Mobile's outputs are portable device dependent.

Specification Differences

The RTX 5080 and RTX 5090 Mobile differ in several key specifications beyond the core counts. Memory capacity is one: the 5080 has 16 GB, the 5090 Mobile has 24 GB. Both use GDDR7 on a 256-bit bus, but memory clocks differ. The 5080 runs at 1875 MHz with 30 Gbps effective speed, yielding 960.0 GB/s bandwidth. The 5090 Mobile runs at 1750 MHz with 28 Gbps effective speed, yielding 896.0 GB/s bandwidth. The desktop card has 64 GB/s more bandwidth.

Pixel and texture rates reflect the clock differences. The RTX 5080 achieves 293.1 GPixel/s and 879.3 GTexel/s. The RTX 5090 Mobile achieves 169.7 GPixel/s and 496.9 GTexel/s. FP32 and FP16 compute are both 56.28 TFLOPS for the 5080 (1:1 ratio) and 31.80 TFLOPS for the 5090 Mobile (1:1 ratio). The desktop card delivers 24.48 more TFLOPS of FP32 performance.

Form factor and power draw separate the two clearly. The RTX 5080 is dual-slot, 304 mm long, 137 mm tall, and 40 mm wide, with a 360 W TDP. The RTX 5090 Mobile is an IGP with no dimensions listed and a 95 W TDP. The mobile part requires no power connectors, while the desktop card needs a 16-pin connector.

Release dates differ: the RTX 5080 launched on 2025-01-29, the RTX 5090 Mobile on 2025-03-26. The desktop card has a successor (GeForce 60), while the mobile part does not. The 5080 has a launch MSRP of 999 USD. The 5090 Mobile has no listed launch MSRP.

Head-to-Head Benchmarks

The RTX 5080 wins all 10 head-to-head tests. The largest margin is in Passmark GPU Compute: 21789 versus 13401, a 62.6% lead. This test stresses raw compute throughput, and the desktop card's higher clocks and 24.48 more TFLOPS of FP32 performance show clearly. The 5080's 56.28 TFLOPS versus 31.80 TFLOPS explains the gap.

The second-largest margin is in 3DMark Steel Nomad DX12: 8637 versus 5871, a 47.1% difference. This modern DX12 test benefits from the 5080's higher pixel rate (293.1 GPixel/s versus 169.7 GPixel/s) and texture rate (879.3 GTexel/s versus 496.9 GTexel/s). The desktop card's 960.0 GB/s bandwidth also edges out the mobile part's 896.0 GB/s.

Geekbench Vulkan shows a 28.8% lead for the 5080: 255450 versus 198405. This API-level test benefits from the higher shading unit count and boost clock. The 5080's 10752 shading units versus 10496 is a small edge, but the 2617 MHz boost versus 1515 MHz creates a substantial throughput advantage.

Passmark G2D shows a 33.9% lead: 1415 versus 1057. This 2D test reflects memory bandwidth and clock speeds, where the 5080's 960.0 GB/s and 2617 MHz boost outperform the mobile part's 896.0 GB/s and 1515 MHz boost.

Passmark G3D shows a 21.7% lead: 36565 versus 30034. This general 3D test combines multiple factors, and the 5080's higher texture rate (879.3 GTexel/s versus 496.9 GTexel/s) and pixel rate (293.1 GPixel/s versus 169.7 GPixel/s) drive the result.

Geekbench OpenCL shows a 16.9% lead: 235901 versus 201834. This compute test benefits from the 5080's higher FP32 throughput, though the gap is smaller than in Passmark GPU Compute due to different workload characteristics.

Passmark DirectX 11 shows a 20.4% lead: 324 versus 269. Passmark DirectX 9 shows a 20.1% lead: 389 versus 324. Passmark DirectX 10 shows a 13.7% lead: 208 versus 183. Passmark DirectX 12 shows the smallest margin at 9.4%: 151 versus 138. The DX12 result suggests that when both GPUs use modern rendering paths, the mobile part's lower clocks are less of a liability.

The RTX 5080's average benchmark score of 56083 places it 0.6% ahead of the AMD Radeon 8060S (55757) and 0.7% ahead of the AMD Radeon RX 6750 GRE 12 GB (55698). It trails the AMD Radeon RX 9070 GRE (57367) by 2.2%. The RTX 5090 Mobile's average of 45152 sits 0.8% ahead of the NVIDIA GeForce RTX 4070 Ti (44795), 0.5% behind the AMD Radeon Pro 5500 XT (45384), 1% behind the Intel Arc A730M (45592), and 1.8% behind the NVIDIA RTX 5880 Ada Generation (45972).

The Verdict

The NVIDIA GeForce RTX 5080 is the superior GPU in every recorded benchmark. It wins all 10 head-to-head tests, with margins ranging from 9.4% in Passmark DirectX 12 to 62.6% in Passmark GPU Compute. Its higher boost clock (2617 MHz versus 1515 MHz), higher FP32 throughput (56.28 TFLOPS versus 31.80 TFLOPS), and higher memory bandwidth (960.0 GB/s versus 896.0 GB/s) make it the clear choice for desktop systems where power and space are not constraints.

The RTX 5090 Mobile, despite losing every test, serves a different purpose. Its 95 W TDP and IGP form factor make it suitable for portable devices, where the 5080's 360 W TDP and dual-slot footprint are impossible. The mobile part also offers 24 GB of memory versus 16 GB, which matters for large datasets or high-resolution textures. Its 84th percentile ranking versus the 5080's 87th shows it remains a strong GPU overall.

Users building a desktop should choose the RTX 5080 for its decisive performance lead. Users who need a laptop or compact device should choose the RTX 5090 Mobile, accepting lower scores in exchange for portability. The data does not support any scenario where the mobile part wins on performance, but its memory capacity and power efficiency make it the appropriate pick for mobile systems. The RTX 5080's launch MSRP is 999 USD.