AMD Radeon RX 480 vs NVIDIA GeForce RTX 5090 Mobile Comparison

Head-to-Head Benchmarks

The recorded data shows a decisive sweep for the NVIDIA GeForce RTX 5090 Mobile across all three shared benchmark tests. In 3DMark Steel Nomad (DX12), the RTX 5090 Mobile scores 5871, while the AMD Radeon RX 480 scores 966. This translates to a 507.8% advantage, the largest delta in the head-to-head set. The margin is so wide that the NVIDIA part is operating in a completely different performance class; the RX 480’s score is closer to a fraction of the RTX 5090 Mobile’s output than to a competitor’s result.

In Geekbench OpenCL, the RTX 5090 Mobile posts 201834 against 37998 for the RX 480, a 431.2% lead. This test leans on raw compute throughput, and the gap reflects the stark difference in shading resources and memory bandwidth. The Geekbench Vulkan result follows the same pattern: the NVIDIA GPU scores 198405, the AMD GPU scores 45968, a 331.6% lead. Even the smallest of the three wins is still a multi-fold difference. The RX 480’s best showing is in Vulkan, where its score reaches 45968, but that remains only 23.2% of the RTX 5090 Mobile’s Vulkan result.

For broader context, the RTX 5090 Mobile’s average benchmark score is 45152, placing it in the 84th percentile of all GPUs. Its nearest rivals in the database include the AMD Radeon Pro 5500 XT (45384, a 0.5% gap), the NVIDIA GeForce RTX 4070 Ti (44795, 0.8% ahead of the rival), the Intel Arc A730M (45592, 1% behind), and the NVIDIA RTX 5880 Ada Generation (45972, 1.8% behind). These deltas are small, meaning the RTX 5090 Mobile sits in a tightly packed band of high-end performers. Meanwhile, the RX 480’s average score is 33997, placing it in the 78th percentile, with rivals like the AMD Radeon HD 7950 (33951, 0.1% ahead), the AMD Radeon RX 560 XT (34133, 0.4% behind), the AMD Radeon RX 7700S (33849, 0.4% ahead), and the NVIDIA RTX A2000 12 GB (34154, 0.5% behind). The RX 480 is similarly clustered with its own peers, but that cluster sits roughly 33% lower in average score than the RTX 5090 Mobile’s cluster.

Architecture Differences

The architectural divide between these two GPUs is generational and fundamental. The RTX 5090 Mobile uses the GB203 chip built on Blackwell 2.0 architecture, fabricated on a 5 nm process at TSMC. It packs 45,600 million transistors on a 378 mm² die, yielding a transistor density of 120.6 million per mm². The RX 480 uses the Ellesmere chip with GCN 4.0 architecture, built on a 14 nm process at GlobalFoundries. It contains 5,700 million transistors on a 232 mm² die, with a density of 24.6 million per mm². The RTX 5090 Mobile has roughly 8 times the transistor count in only 1.63 times the die area.

The compute resources differ just as sharply. The RTX 5090 Mobile has 10496 shading units, 328 TMUs, and 112 ROPs. It also includes 82 RT cores for hardware ray tracing and 328 tensor cores for AI acceleration. The RX 480 has 2304 shading units, 144 TMUs, and 32 ROPs, with no RT cores and no tensor cores. The RTX 5090 Mobile’s pixel rate is 169.7 GPixel/s versus 40.51 GPixel/s for the RX 480. Texture rate is 496.9 GTexel/s versus 182.3 GTexel/s. FP32 throughput is 31.80 TFLOPS for the NVIDIA part, while the AMD part manages 5.834 TFLOPS. Both GPUs offer FP16 at a 1:1 ratio with FP32, but the absolute numbers are far apart.

Memory configurations reinforce the gap. The RTX 5090 Mobile comes with 24 GB of GDDR7 on a 256-bit bus, delivering 896.0 GB/s of bandwidth. The RX 480 has 8 GB of GDDR5 on a 256-bit bus, with 256.0 GB/s of bandwidth. The NVIDIA card has 3.5 times the bandwidth and 3 times the capacity. The RX 480’s memory clock runs at 2000 MHz (8 Gbps effective), while the RTX 5090 Mobile’s memory runs at 1750 MHz (28 Gbps effective); the higher effective data rate is what drives the bandwidth advantage. The bus interface also differs: the RTX 5090 Mobile uses PCIe 5.0 x16, while the RX 480 uses PCIe 3.0 x16.

API support is another differentiator. The RTX 5090 Mobile supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The RX 480 supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.3. The Blackwell part has a more modern feature set, including the hardware ray tracing and tensor cores that the GCN part simply does not have. The RTX 5090 Mobile is listed with an IGP slot width and no power connectors, reflecting its mobile design, while the RX 480 is a dual-slot card with a 1x 6-pin power connector and a suggested PSU of 450 W. The RX 480’s TDP is 150 W, while the RTX 5090 Mobile’s TDP is 95 W, meaning the far faster GPU also reports a lower power draw. The display outputs are portable-device-dependent for the RTX 5090 Mobile, while the RX 480 offers 1x HDMI 2.0b and 3x DisplayPort 1.4a.

Where Each One Wins

The RTX 5090 Mobile wins in every recorded benchmark category shared between the two. Its 3DMark Steel Nomad DX12 result of 5871 is over 6 times the RX 480’s 966. For compute-heavy workloads, the Geekbench OpenCL score of 201834 is more than 5 times the RX 480’s 37998. For Vulkan, the 198405 score is over 4 times the RX 480’s 45968. The only benchmarks available for the RTX 5090 Mobile cover DirectX 10 (183), DirectX 11 (269), DirectX 12 (138), DirectX 9 (324), G2D (1057), G3D (30034), GPU Compute (13401), and OpenCL (201834). The RX 480 has no recorded scores in those DirectX or Passmark tests, so no direct comparison is possible there. However, the RTX 5090 Mobile’s Passmark G3D score of 30034 and GPU Compute score of 13401 are notable on their own, indicating consistent strength across DirectX and compute paths.

The RX 480 does have a Geekbench Metal score of 51057, but the RTX 5090 Mobile has no recorded Metal benchmark in the database, so this is not a head-to-head point. The RX 480’s wins, if any, come only in tests where the RTX 5090 Mobile was not measured. In terms of shared workloads, the data is unambiguous: the RTX 5090 Mobile is faster by margins ranging from 331.6% to 507.8%. The RX 480’s percentile ranking of 78 is respectable, but the RTX 5090 Mobile’s 84th percentile is higher, and its average benchmark score of 45152 versus 33997 shows a 32.8% overall advantage.

The Verdict

The RTX 5090 Mobile is the clear choice for anyone prioritizing maximum performance in modern DirectX 12 and Vulkan workloads, based strictly on the recorded data. The 507.8% lead in 3DMark Steel Nomad DX12 and the 431.2% lead in Geekbench OpenCL demonstrate that the Blackwell architecture, with 10496 shading units, 82 RT cores, 328 tensor cores, 24 GB of GDDR7 memory, and 896.0 GB/s of bandwidth, delivers results that the GCN 4.0 design cannot approach. The RX 480, with 2304 shading units, no RT cores or tensor cores, 8 GB of GDDR5, and 256.0 GB/s of bandwidth, trails by margins that are effectively generational chasms. The RX 480 remains competitive within its own peer group, sitting within 0.5% of the AMD Radeon RX 7700S and 0.1% of the AMD Radeon HD 7950, but those rivals are themselves far below the RTX 5090 Mobile’s cluster.

For users on a legacy workload that requires GCN-era capabilities, the RX 480 can still function, but the database shows no shared test where it closes the gap. The RTX 5090 Mobile also carries a lower reported TDP of 95 W versus 150 W, meaning the performance advantage does not come with a power tradeoff. The RX 480’s end-of-life status and predecessor status as part of the Arctic Islands generation reinforce that its architecture is from an older era. The verdict is simple: the RTX 5090 Mobile wins every shared benchmark, and the margins are so large that no use case based on this data favors the RX 480.

FAQ

Q: Which GPU has the higher 3DMark Steel Nomad DX12 score?

A: The NVIDIA GeForce RTX 5090 Mobile scores 5871, while the AMD Radeon RX 480 scores 966, a 507.8% difference.

Q: How much faster is the RTX 5090 Mobile in Geekbench OpenCL?

A: The RTX 5090 Mobile scores 201834, AMD Radeon RX 480 scores 37998, giving the NVIDIA part a 431.2% lead in Geekbench OpenCL.

Q: Does the RX 480 have ray tracing support in hardware, and does the RTX 5090 Mobile?

A: The RX 480 has no RT cores and no tensor cores, while the RTX 5090 Mobile has 82 RT cores and 328 tensor cores in its Blackwell 2.0 architecture.

Q: What are the memory capacities of the two GPUs?

A: The RTX 5090 Mobile has 24 GB of GDDR7 memory with 896.0 GB/s of bandwidth, while the RX 480 has 8 GB of GDDR5 with 256.0 GB/s of bandwidth.

Q: How do their average benchmark scores compare?

A: The RTX 5090 Mobile has an average benchmark score of 45152, placing it in the 84th percentile, while the RX 480 averages 33997, placing it in the 78th percentile.

Q: Which GPU has a higher TDP?

A: The RTX 5090 Mobile has a TDP of 95 W, and the RX 480 has a TDP of 150 W. The RX 480 is the higher power draw between the two in recorded data.

Specification Differences

The two GPUs differ in the following recorded specification fields: process node (5 nm for the RTX 5090 Mobile, 14 nm for the RX 480), foundry (TSMC for NVIDIA, GlobalFoundries for AMD), transistors (45,600 million versus 5,700 million), die size (378 mm² versus 232 mm²), transistor density (120.6M per mm² versus 24.6M per mm²), base clock (990 MHz versus 1120 MHz), boost clock (1515 MHz versus 1266 MHz), memory clock (1750 MHz 28 Gbps effective versus 2000 MHz 8 Gbps effective), memory size (24 GB versus 8 GB), memory type (GDDR7 versus GDDR5), bandwidth (896.0 GB/s versus 256.0 GB/s), shading units (10496 versus 2304), TMUs (328 versus 144), ROPs (112 versus 32), RT cores (82 versus null), tensor cores (328 versus null), pixel rate (169.7 GPixel/s versus 40.51 GPixel/s), texture rate (496.9 GTexel/s versus 182.3 GTexel/s), FP32 (31.80 TFLOPS versus 5.834 TFLOPS), FP16 (31.80 TFLOPS versus 5.834 TFLOPS), TDP (95 W versus 150 W), slot width (IGP versus Dual-slot), power connectors (None versus 1x 6-pin), suggested PSU (null versus 450 W), bus interface (PCIe 5.0 x16 versus PCIe 3.0 x16), display outputs (Portable Device Dependent versus 1x HDMI 2.0b and 3x DisplayPort 1.4a), DirectX support (12 Ultimate 12_2 versus 12_0), Vulkan support (1.4 versus 1.3), production status (Active versus End-of-life), release date (2025-03-26 versus 2016-06-28), and predecessor (GeForce 40 Mobile versus Pirate Islands). The RX 480 also has a successor listed as Polaris, while the RTX 5090 Mobile has no successor. The RX 480 has a launch MSRP of 229 USD.