AMD Radeon RX Vega 64 vs NVIDIA GeForce RTX 5090 Mobile Comparison

The AMD Radeon RX Vega 64 and NVIDIA GeForce RTX 5090 Mobile represent two vastly different eras of GPU design, with the former being an end-of-life desktop flagship from 2017 and the latter an active mobile solution from 2025. The data shows a decisive performance gap, but the comparison is far more nuanced than a simple scoreboard, given their divergent architectures, power profiles, and intended use cases. This analysis examines the benchmark results, architectural philosophies, and specification differences to determine what each GPU offers in its respective context.

Head-to-Head Benchmarks

The benchmark data is unambiguous: the NVIDIA GeForce RTX 5090 Mobile dominates every shared test. In the 3DMark Steel Nomad DX12 test, the RTX 5090 Mobile scores 5871, which is 71.6% ahead of the RX Vega 64’s 1669. This is not a marginal victory; it is a generational leap that reflects the RTX 5090 Mobile’s modern architecture and significantly higher raw compute resources.

The gap persists across compute-focused workloads. In Geekbench OpenCL, the RTX 5090 Mobile posts 201834 against the RX Vega 64’s 62552, a 69% advantage. The Vulkan test tells a similar story: 198405 versus 67032, a 66.2% lead for NVIDIA. These results indicate that the RTX 5090 Mobile is not just faster in gaming-oriented DX12 workloads but also in general-purpose GPU compute, which is a critical consideration for content creators and researchers.

Notably, the RX Vega 64 has zero wins across the three shared benchmarks. This is a complete sweep for NVIDIA. However, the RX Vega 64’s average benchmark score of 50001 places it in the 86th percentile of all GPUs, while the RTX 5090 Mobile’s average of 45152 sits in the 84th percentile. This apparent contradiction—where the older card has a higher percentile despite losing every head-to-head—is explained by the fact that the RTX 5090 Mobile’s average is dragged down by its Passmark DX9, DX10, DX11, and DX12 scores (324, 183, 269, and 138 respectively), which are likely from a different testing methodology or driver state. The RX Vega 64’s average is based solely on its stronger Geekbench and 3DMark results, making the percentiles less directly comparable.

The Verdict

Based strictly on the benchmark data, the NVIDIA GeForce RTX 5090 Mobile is the superior performer for anyone prioritizing raw speed. It wins 100% of the shared tests, with leads ranging from 66.2% to 71.6%. The RTX 5090 Mobile’s 31.80 TFLOPS FP32 throughput, 896.0 GB/s memory bandwidth, and 24 GB of GDDR7 memory provide a foundational advantage that the RX Vega 64’s 12.66 TFLOPS, 483.8 GB/s, and 8 GB of HBM2 cannot overcome.

However, the verdict is not a simple recommendation for NVIDIA. The RTX 5090 Mobile is a mobile IGP with a 95 W TDP, meaning it is designed for laptops where power efficiency is paramount. The RX Vega 64 is a dual-slot desktop card with a 295 W TDP and two 8-pin power connectors, requiring a 600 W PSU. If the use case is a desktop workstation where power draw is not a constraint, the RX Vega 64’s 86th percentile ranking and average score of 50001—which is remarkably close to the RTX 5090 Mobile’s 84th percentile and 45152 average—suggest it remains a capable contender in broader GPU comparisons. The data implies that the RTX 5090 Mobile is the better choice for mobile performance, while the RX Vega 64 is a viable option for desktop users who value its specific benchmark profile.

Where Each One Wins

The RTX 5090 Mobile wins decisively in every shared benchmark category. In 3DMark Steel Nomad DX12, it demonstrates superior gaming performance, which is critical for high-refresh-rate laptop gaming. In Geekbench OpenCL and Vulkan, it excels in compute-heavy tasks like 3D rendering, machine learning inference, and video encoding, where its 82 RT cores and 328 tensor cores provide hardware acceleration that the RX Vega 64 lacks entirely.

The RX Vega 64, despite losing all head-to-head tests, has its own niche. Its 86th percentile ranking indicates it performs well relative to the entire GPU landscape, and its average score of 50001 is only 0.1% behind the NVIDIA GeForce RTX 5070 Ti (49957) and 1.9% ahead of the AMD Radeon RX 6900 XT (50951). This suggests that in desktop scenarios where the RTX 5090 Mobile cannot physically be installed, the RX Vega 64 holds its own against modern desktop rivals. Its 2048-bit memory bus, while narrower than the RTX 5090 Mobile’s 256-bit bus, is paired with HBM2 to deliver respectable bandwidth, and its 4096 shading units are sufficient for 1440p and even some 4K workloads in older titles.

FAQ

Q: Which GPU is faster in the 3DMark Steel Nomad DX12 test?

A: The NVIDIA GeForce RTX 5090 Mobile scores 5871, which is 71.6% higher than the AMD Radeon RX Vega 64’s 1669.

Q: How do the two GPUs compare in compute performance?

A: In Geekbench OpenCL, the RTX 5090 Mobile scores 201834 versus 62552 for the RX Vega 64, a 69% advantage. In Vulkan, the RTX 5090 Mobile leads with 198405 against 67032, a 66.2% difference.

Q: What is the memory configuration difference?

A: The RX Vega 64 has 8 GB of HBM2 on a 2048-bit bus with 483.8 GB/s bandwidth. The RTX 5090 Mobile has 24 GB of GDDR7 on a 256-bit bus with 896.0 GB/s bandwidth.

Q: Are there any tests where the AMD card wins?

A: No. Across the three shared benchmarks (3DMark Steel Nomad, Geekbench OpenCL, and Geekbench Vulkan), the RTX 5090 Mobile wins all of them.

Q: How do their overall percentile rankings compare?

A: The RX Vega 64 is in the 86th percentile of all GPUs, while the RTX 5090 Mobile is in the 84th percentile. This is based on their respective average benchmark scores of 50001 and 45152.

Q: What is the TDP difference between the two?

A: The RX Vega 64 has a 295 W TDP and requires a 600 W PSU with two 8-pin connectors. The RTX 5090 Mobile has a 95 W TDP and uses no power connectors, as it is an integrated mobile GPU.

Architecture Differences

The architectural divide is stark. The RX Vega 64 uses the Vega 10 chip on a 14 nm GlobalFoundries process, featuring 12,500 million transistors on a 495 mm² die. Its GCN 5.0 architecture is a mature design from 2017, with 4096 shading units, 256 TMUs, and 64 ROPs. It has no dedicated RT or tensor cores, meaning ray tracing and AI-accelerated workloads are handled by general-purpose shaders, which is inefficient.

The RTX 5090 Mobile is built on the GB203 chip using TSMC’s 5 nm process, packing 45,600 million transistors into a 378 mm² die. Its Blackwell 2.0 architecture is fundamentally different, with 10496 shading units, 328 TMUs, and 112 ROPs, but crucially it adds 82 RT cores and 328 tensor cores. This hardware specialization allows the RTX 5090 Mobile to handle ray tracing and tensor operations (like DLSS) at hardware speed, something the RX Vega 64 cannot do. The RTX 5090 Mobile also supports DirectX 12 Ultimate (12_2) and Vulkan 1.4, while the RX Vega 64 is limited to DirectX 12 (12_1) and Vulkan 1.3.

Specification Differences

The two GPUs differ on nearly every measurable specification. The process node is 14 nm for AMD versus 5 nm for NVIDIA. Transistor count is 12,500 million versus 45,600 million, and die size is 495 mm² versus 378 mm², resulting in transistor densities of 25.3M/mm² and 120.6M/mm² respectively. Clock speeds show the RX Vega 64 boosting to 1546 MHz, while the RTX 5090 Mobile boosts to 1515 MHz—a surprisingly small difference given the architectural gap.

Memory is a major differentiator: 8 GB HBM2 versus 24 GB GDDR7, with bus widths of 2048-bit versus 256-bit. Bandwidth is 483.8 GB/s versus 896.0 GB/s. Compute throughput is 12.66 TFLOPS FP32 versus 31.80 TFLOPS FP32, and FP16 is 25.33 TFLOPS (2:1) versus 31.80 TFLOPS (1:1). Pixel rate is 98.94 GPixel/s versus 169.7 GPixel/s, and texture rate is 395.8 GTexel/s versus 496.9 GTexel/s. Power draw is a massive difference: 295 W versus 95 W, with the RX Vega 64 requiring dual-slot cooling and 2x 8-pin connectors, while the RTX 5090 Mobile is an IGP with no external power connectors. The bus interface is PCIe 3.0 x16 versus PCIe 5.0 x16, and display outputs are 1x HDMI 2.0b and 3x DisplayPort 1.4a versus being portable device dependent. The RX Vega 64 has a launch MSRP of 499 USD, while the RTX 5090 Mobile has no MSRP listed.