AMD Radeon Pro 580 vs NVIDIA GeForce RTX 5090 Mobile Comparison

The NVIDIA GeForce RTX 5090 Mobile and AMD Radeon Pro 580 represent two extremes of the mobile GPU spectrum, separated by nearly eight years of architecture evolution. The data reveals a decisive performance gap, yet the Radeon Pro 580 still holds relevance in specific legacy contexts. Benchmark results show the RTX 5090 Mobile dominating the shared test suite, but the comparison is far more nuanced than raw score differences alone, as the two cards target entirely different ecosystems and workloads.

Head-to-Head Benchmarks

The head-to-head data is stark, with the NVIDIA GeForce RTX 5090 Mobile winning both shared benchmarks by massive margins. In Geekbench OpenCL, the RTX 5090 Mobile scores 201,834 against the Radeon Pro 580’s 38,457, a delta of 424.8% — the newer card delivers over five times the raw compute throughput. This is not a marginal improvement; it is a generational leap that reflects the shift from a 14 nm process with 5,700 million transistors to a 5 nm node with 45,600 million transistors.

The Vulkan results tell a similar story, though with a slightly narrower gap. The RTX 5090 Mobile posts 198,405 versus 43,285 for the Radeon Pro 580, a 358.4% advantage. Notably, the Radeon Pro 580’s Vulkan score is its strongest benchmark, beating its own OpenCL result by roughly 12.5%. This suggests the older GCN 4.0 architecture handles Vulkan’s explicit control model better than OpenCL, but it is nowhere near enough to close the chasm. The RTX 5090 Mobile’s Vulkan score is about 1.7% lower than its OpenCL score, indicating a more balanced API performance profile.

Looking at broader benchmark averages, the RTX 5090 Mobile holds an average score of 45,152 across ten tests, while the Radeon Pro 580 averages 40,318 across just three. This smaller average gap — roughly 12% — is misleading because the RTX 5090 Mobile’s suite includes demanding DirectX 12 and PassMark tests where it scores 30,034 in G3D and 13,401 in GPU compute. The Radeon Pro 580 simply has no comparable data points, as its benchmark set is limited to Geekbench workloads, which historically favor compute-heavy tasks over gaming rasterization.

The RTX 5090 Mobile’s nearest rivals in the overall database include the AMD Radeon Pro 5500 XT at 45,384 (0.5% higher), the NVIDIA GeForce RTX 4070 Ti at 44,795 (0.8% lower), and the Intel Arc A730M at 45,592 (1% higher). This places the RTX 5090 Mobile in a tightly contested mid-to-high tier, where it trades blows with desktop-class cards from the previous generation. Meanwhile, the Radeon Pro 580’s closest competitor is the NVIDIA GeForce RTX 5070 at 40,377, a mere 0.1% difference, showing the aging AMD card still performs near modern entry-level discrete GPUs.

The Verdict

From the data, the NVIDIA GeForce RTX 5090 Mobile is the unequivocal winner for any modern workload. Its 424.8% lead in OpenCL and 358.4% lead in Vulkan are not just wins; they are category-defining margins. The card’s 84th percentile ranking among all GPUs, versus the Radeon Pro 580’s 82nd, further confirms its superior standing, though the percentiles are closer than the raw scores suggest — indicating the older card still outperforms a majority of the GPU population. The RTX 5090 Mobile is a production-status product with a 2025 release, while the Radeon Pro 580 is end-of-life from 2017, so any rational purchase decision based on performance alone favors NVIDIA.

However, the Radeon Pro 580 is not without a data-driven rationale. Its 185 W TDP is nearly double the RTX 5090 Mobile’s 95 W, yet it delivers only a fraction of the performance. This makes the RTX 5090 Mobile vastly more efficient, but the Radeon Pro 580’s lower transistor count and simpler architecture might appeal to users requiring legacy driver support or specific macOS compatibility, given its generation label of "Radeon Pro Mac (500 Series)." The RTX 5090 Mobile’s average score of 45,152 versus the Radeon Pro 580’s 40,318 shows a 12% overall advantage, but the newer card’s benchmark suite is far more comprehensive, suggesting the real-world gap in gaming and DirectX 12 workloads would be even larger.

Where Each One Wins

The RTX 5090 Mobile wins every measurable category in the shared tests, but its strengths are most pronounced in compute-heavy OpenCL workloads, where it achieves a 424.8% delta. This suggests it is ideal for AI inference, scientific simulations, and content creation tasks that leverage FP32 and FP16 compute — both rated at 31.80 TFLOPS. Its 24 GB of GDDR7 memory with 896.0 GB/s bandwidth provides 10.7 times the memory bandwidth of the Radeon Pro 580’s 217.0 GB/s, making it superior for large datasets and high-resolution textures. The Vulkan win at 358.4% also positions it for modern cross-platform game engines and compute APIs.

The Radeon Pro 580, despite its losses, shows one clear niche: legacy API performance. Its Vulkan score of 43,285 is its best result, and it supports DirectX 12 (12_0) and OpenGL 4.6, albeit without ray tracing or tensor cores. For users running older software that relies on GCN 4.0’s specific instruction set, the card remains functional, as evidenced by its 82nd percentile ranking. Its 8 GB GDDR5 memory is half the RTX 5090 Mobile’s capacity, but for 1080p or 1440p workloads from its 2017 era, this is sufficient. The Radeon Pro 580’s PCIe 3.0 x16 interface, versus the RTX 5090 Mobile’s PCIe 5.0 x16, also means it can plug into older systems without bottlenecking, though it caps transfer speeds.

FAQ

Q: Which GPU has the higher benchmark score in Geekbench OpenCL?

A: The NVIDIA GeForce RTX 5090 Mobile scores 201,834, which is 424.8% higher than the AMD Radeon Pro 580’s 38,457.

Q: How do the two cards compare in Vulkan performance?

A: The RTX 5090 Mobile leads with 198,405 versus 43,285 for the Radeon Pro 580, a 358.4% advantage for NVIDIA.

Q: What is the average benchmark score difference between the two?

A: The RTX 5090 Mobile averages 45,152 across ten tests, while the Radeon Pro 580 averages 40,318 across three, giving NVIDIA a 12% overall lead.

Q: Which card has better memory bandwidth?

A: The RTX 5090 Mobile offers 896.0 GB/s from 24 GB GDDR7, while the Radeon Pro 580 provides 217.0 GB/s from 8 GB GDDR5.

Q: Are there any benchmarks where the Radeon Pro 580 wins?

A: In the head-to-head data, the Radeon Pro 580 wins zero benchmarks. Its best relative performance is in Vulkan, where it scores 43,285, but this is still far behind NVIDIA.

Q: What are the production statuses of these GPUs?

A: The RTX 5090 Mobile is listed as Active with a release date of 2025-03-26, while the Radeon Pro 580 is End-of-life from 2017-06-04.

Architecture Differences

The architectural gap between these two GPUs is immense, starting with the manufacturing process. The RTX 5090 Mobile uses a 5 nm node at TSMC, packing 45,600 million transistors into a 378 mm² die for a density of 120.6 million transistors per mm². The Radeon Pro 580, built on GlobalFoundries’ 14 nm process, contains only 5,700 million transistors on a 232 mm² die, yielding 24.6 million per mm² — a 4.9x density advantage for NVIDIA. This allows the RTX 5090 Mobile to house 10,496 shading units, 328 TMUs, and 112 ROPs, versus 2,304 shading units, 144 TMUs, and 32 ROPs on the Radeon Pro 580.

The RTX 5090 Mobile’s Blackwell 2.0 architecture brings dedicated hardware that the Radeon Pro 580 lacks entirely: 82 ray tracing cores and 328 tensor cores. The Radeon Pro 580’s GCN 4.0 architecture has no such units, meaning it cannot accelerate ray tracing or AI workloads in hardware. Clock speeds differ as well: the RTX 5090 Mobile runs at 990 MHz base and 1515 MHz boost, while the Radeon Pro 580 operates at 1100 MHz base and 1200 MHz boost. Despite lower clocks, the RTX 5090 Mobile achieves 31.80 TFLOPS FP32 versus 5.530 TFLOPS for the Radeon Pro 580, a 5.75x advantage driven by core count and efficiency.

API support also diverges. The RTX 5090 Mobile supports DirectX 12 Ultimate (12_2), Vulkan 1.4, and OpenGL 4.6, while the Radeon Pro 580 tops out at DirectX 12 (12_0), Vulkan 1.3, and OpenGL 4.6. The newer card’s PCIe 5.0 x16 interface doubles the bandwidth of the Radeon Pro 580’s PCIe 3.0 x16, which is critical for feeding the RTX 5090 Mobile’s 896.0 GB/s memory pipeline. Both cards are IGP (integrated graphics processor) form factors with no power connectors, but the Radeon Pro 580 draws 185 W versus 95 W for the RTX 5090 Mobile, making the NVIDIA part more than twice as power-efficient per watt of performance.

Specification Differences

The most glaring specification difference is memory: the RTX 5090 Mobile has 24 GB of GDDR7 on a 256-bit bus, while the Radeon Pro 580 has 8 GB of GDDR5 on the same 256-bit bus. This yields bandwidth of 896.0 GB/s versus 217.0 GB/s, a 4.1x gap. Memory clocks also differ: the RTX 5090 Mobile runs at 1750 MHz with 28 Gbps effective, while the Radeon Pro 580 operates at 1695 MHz with 6.8 Gbps effective. The shading unit count is 10,496 versus 2,304, and TMUs are 328 versus 144, while ROPs are 112 versus 32.

Pixel and texture rates reinforce the performance divide: the RTX 5090 Mobile achieves 169.7 GPixel/s and 496.9 GTexel/s, versus 38.40 GPixel/s and 172.8 GTexel/s for the Radeon Pro 580. The FP16 compute is identical to FP32 on both cards at 1:1 ratio, but the absolute numbers differ wildly: 31.80 TFLOPS versus 5.530 TFLOPS. The RTX 5090 Mobile has a base clock of 990 MHz and boost of 1515 MHz, while the Radeon Pro 580 has a higher base clock of 1100 MHz but a lower boost of 1200 MHz. The TDP difference is substantial: 95 W for NVIDIA versus 185 W for AMD. Both use a PCIe x16 interface, but the RTX 5090 Mobile is PCIe 5.0 while the Radeon Pro 580 is PCIe 3.0. Display outputs are "Portable Device Dependent" for both, and neither has a launch MSRP listed in the data.