AMD Radeon 780M vs NVIDIA GeForce RTX 5090 D V2 Comparison

The AMD Radeon 780M and the NVIDIA GeForce RTX 5090 D V2 represent two extreme poles of the graphics hardware spectrum: a 15-watt integrated processor and a 575-watt flagship add-in board. The single head-to-head benchmark available in the data, 3DMark Steel Nomad (DX12), shows a decisive victory for the NVIDIA part, scoring 16,504 points against the AMD's 480 points. This translates to a delta of -97.1% for the AMD part, meaning the RTX 5090 D V2 is over 34 times faster in this specific test.

Head-to-Head Benchmarks

The only directly comparable data point is the 3DMark Steel Nomad DX12 test, and the result is not close. The NVIDIA GeForce RTX 5090 D V2 delivers a score of 16,504, while the AMD Radeon 780M manages just 480. This represents a 97.1% deficit for the integrated GPU, a gap so large that it dwarfs any other comparison.

Looking at the broader benchmark averages, the disparity remains stark, though the delta narrows due to the inclusion of other test types. The AMD Radeon 780M has an average benchmark score of 17,588, which is actually higher than the RTX 5090 D V2's average of 16,504. This counterintuitive result is explained by the fact that the AMD part's average includes scores from Geekbench OpenCL (18,602) and Geekbench Vulkan (33,683), which are compute-oriented tests that favor its architecture. The NVIDIA part's average is based solely on its single 3DMark Steel Nomad result, a pure gaming workload.

Examining the nearest rivals provides further context for each GPU's standing. The AMD Radeon 780M sits at the 61st percentile of all GPUs, with its closest competitor being the NVIDIA GeForce RTX 4060, which has an average score of 17,639 and a delta of -0.3%. The AMD part also edges out the AMD Radeon Pro 560 by 0.2% and trails the AMD Radeon HD 7790 by 0.4%. This places the integrated solution within a narrow performance band of older discrete cards.

The NVIDIA GeForce RTX 5090 D V2, despite its massive raw power in the Steel Nomad test, sits at the 59th percentile in the database, slightly below the AMD part. Its nearest rival is the NVIDIA T400, with an average score of 16,508 and a delta of 0%. This indicates that the database's average score, which is heavily weighted by compute benchmarks, does not reflect the NVIDIA part's gaming dominance. The RTX 5090 D V2 is 0.5% ahead of the AMD Radeon PRO W7500 and 0.9% ahead of the AMD Radeon RX 5700 XT in average score.

The data implies a fundamental split: in rasterized gaming workloads like 3DMark Steel Nomad, the NVIDIA part is in a different universe. In compute-heavy tasks, the AMD part's architecture proves surprisingly competitive, even surpassing the flagship in aggregate. The 3DMark score of 480 for the 780M is a clear indicator of its limitations for high-end gaming, while the RTX 5090 D V2's Geekbench scores are simply absent from the data, leaving a question mark over its compute performance relative to its gaming might.

The Verdict

For gamers, the data is unambiguous. The NVIDIA GeForce RTX 5090 D V2 is the only choice, delivering a 3DMark Steel Nomad score of 16,504 against the AMD Radeon 780M's 480. Anyone seeking to play modern titles at high settings and resolutions would find the integrated GPU entirely inadequate. The RTX 5090 D V2 is built for this purpose, and the benchmark confirms it.

For users whose primary workload is compute or content creation, the verdict is more nuanced. The AMD Radeon 780M's average benchmark score of 17,588, bolstered by its Geekbench Vulkan score of 33,683, suggests it can handle certain parallel processing tasks surprisingly well for an IGP. However, this is relative to its power envelope. The NVIDIA part, while lacking Geekbench scores in the data, would likely dominate in any compute task that utilizes its 104.8 TFLOPS of FP32 performance.

The choice hinges on the workload. If the question is "which GPU produces higher frame rates in demanding games?", the answer is the RTX 5090 D V2 by a margin of 97.1%. If the question is "which GPU offers a better balance of compute performance per watt?", the AMD part's 15-watt TDP versus 575 watts for the NVIDIA part makes a compelling qualitative argument, though the raw performance crown belongs to NVIDIA.

Architecture Differences

The two GPUs are built on fundamentally different architectures and process nodes. The AMD Radeon 780M uses the RDNA 3.0 architecture on a 4 nm process at TSMC, while the NVIDIA GeForce RTX 5090 D V2 uses the Blackwell 2.0 architecture on a 5 nm process, also at TSMC. This means the AMD part is fabricated on a denser process node, achieving a transistor density of 142.6M per mm², compared to the NVIDIA part's 122.9M per mm².

The chip designs reflect their purposes. The AMD part, codenamed Phoenix, is a compact 178 mm² die with 25,390 million transistors. The NVIDIA part, codenamed GB202, is a massive 750 mm² die with 92,200 million transistors. The NVIDIA part has nearly four times the transistors on a die that is over four times larger.

Feature sets also diverge. The AMD Radeon 780M includes 12 ray tracing cores, while the RTX 5090 D V2 includes 170 RT cores. The NVIDIA part also features 680 tensor cores, a hardware component entirely absent from the AMD IGP specification. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, but the underlying hardware implementations are completely different.

The AMD part is an integrated graphics processor (IGP), meaning it shares system memory and has no dedicated VRAM. The NVIDIA part is a discrete GPU with its own 24 GB of GDDR7 memory. This fundamental architectural difference dictates the performance envelope: the AMD part is designed for efficiency and basic tasks, while the NVIDIA part is designed for maximum throughput.

Specification Differences

The specification sheets for these two GPUs read like they belong to different product categories, which they do. The most obvious difference is in power: the AMD Radeon 780M has a TDP of 15 W and requires no power connectors, while the NVIDIA GeForce RTX 5090 D V2 has a TDP of 575 W and requires a single 16-pin power connector, with a suggested PSU of 950 W.

Clock speeds differ substantially. The AMD part has a base clock of 800 MHz and a boost clock of 2900 MHz. The NVIDIA part has a base clock of 2017 MHz and a boost clock of 2407 MHz. Despite the lower boost clock, the NVIDIA part's massive core count produces far higher throughput.

The compute resources are starkly different. The AMD Radeon 780M has 768 shading units, 48 TMUs, and 32 ROPs. The NVIDIA GeForce RTX 5090 D V2 has 21,760 shading units, 680 TMUs, and 176 ROPs. This leads to a pixel rate of 92.80 GPixel/s for the AMD part versus 423.6 GPixel/s for the NVIDIA part, and a texture rate of 139.2 GTexel/s versus 1,636.8 GTexel/s.

Memory configuration is also a major divider. The AMD Radeon 780M uses "System Shared" memory with system-dependent bandwidth. The NVIDIA part features 24 GB of GDDR7 on a 384-bit bus, delivering 1.34 TB/s of bandwidth. The bus interface differs as well: PCIe 4.0 x8 for the AMD IGP versus PCIe 5.0 x16 for the NVIDIA card. The physical footprint is also different, with the AMD part being an IGP and the NVIDIA card being a dual-slot, 304 mm long expansion card.

FAQ

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

A: The NVIDIA GeForce RTX 5090 D V2 is vastly faster, scoring 16,504 points compared to the AMD Radeon 780M's 480 points, a delta of -97.1%.

Q: Does the AMD Radeon 780M have a higher average benchmark score?

A: Yes. The AMD Radeon 780M has an average benchmark score of 17,588, which is higher than the NVIDIA GeForce RTX 5090 D V2's average score of 16,504, due to the AMD part's strong Geekbench results.

Q: What is the TDP difference between the two GPUs?

A: The AMD Radeon 780M has a TDP of 15 W, while the NVIDIA GeForce RTX 5090 D V2 has a TDP of 575 W. This is a difference of 560 W.

Q: How much memory does the NVIDIA GeForce RTX 5090 D V2 have?

A: The NVIDIA GeForce RTX 5090 D V2 has 24 GB of GDDR7 memory on a 384-bit bus, with a bandwidth of 1.34 TB/s.

Q: Which GPU has more shading units?

A: The NVIDIA GeForce RTX 5090 D V2 has 21,760 shading units, while the AMD Radeon 780M has 768 shading units.

Q: Does the AMD Radeon 780M have tensor cores?

A: The specification data for the AMD Radeon 780M lists tensor cores as null. The NVIDIA GeForce RTX 5090 D V2 has 680 tensor cores.

Where Each One Wins

NVIDIA GeForce RTX 5090 D V2 wins in: Pure rasterized gaming performance, as proven by its 16,504 score in 3DMark Steel Nomad DX12. It also wins in raw compute throughput with 104.8 TFLOPS of FP32 performance, and in memory bandwidth with 1.34 TB/s. It wins for users who need a discrete, high-power solution with dedicated 24 GB of GDDR7 memory and a PCIe 5.0 x16 interface. It wins in any scenario where maximum frame rates and high-resolution textures are the priority.

AMD Radeon 780M wins in: Efficiency, with a 15 W TDP that is 560 W lower than the NVIDIA part. It wins in aggregate benchmark scores, with an average of 17,588 versus 16,504, driven by its Geekbench Vulkan score of 33,683. It wins for users who need an integrated solution with no power connectors, no slot width, and system-dependent memory. It wins in compact form factors and low-power systems where a discrete GPU is not feasible. The data shows it is competitive in compute-oriented tasks despite its gaming limitations.