AMD Radeon RX 7800 XT vs NVIDIA GeForce GTX 590 Comparison

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 590 has an average benchmark score of 12830, while the AMD Radeon RX 7800 XT has an average score of 11627. The GTX 590 sits at the 52nd percentile of all GPUs, while the RX 7800 XT sits at the 51st percentile.

Q: What is the single recorded head-to-head benchmark result?

A: The database contains one direct comparison in Geekbench OpenCL. The RX 7800 XT scored 18290, while the GTX 590 scored 12830, a difference of 29.9% in favor of the AMD card.

Q: How do the nearest rivals compare for each card?

A: For the GTX 590, the closest rival is the AMD Radeon Pro 455 with a score of 12831 (0% difference). For the RX 7800 XT, the closest rival is the NVIDIA GeForce GTX 1660 with a score of 11680 (-0.5% difference).

Q: What are the memory specifications for each card?

A: The GTX 590 has 1536 MB of GDDR5 memory on a 384-bit bus with 164.0 GB/s bandwidth. The RX 7800 XT has 16 GB of GDDR6 memory on a 256-bit bus with 624.1 GB/s bandwidth.

Q: When were these cards released?

A: The GTX 590 was released on 2011-03-23, while the RX 7800 XT was released on 2023-09-05. The GTX 590 is marked as end-of-life, while the RX 7800 XT remains active in production.

Q: What API support does each card offer?

A: The GTX 590 supports DirectX 12 (11_0) and OpenGL 4.6, but lists no Vulkan support. The RX 7800 XT supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Architecture Differences

The two GPUs represent radically different design eras. The GTX 590 uses the GF110 chip built on Fermi 2.0 architecture, fabricated on a 40 nm process at TSMC. It packs 3,000 million transistors into a 520 mm² die, yielding a density of 5.8 million transistors per square millimeter. The RX 7800 XT uses the Navi 32 chip with RDNA 3.0 architecture, also made by TSMC but on a 5 nm process. This card integrates 28,100 million transistors into a smaller 346 mm² die, achieving 81.2 million transistors per square millimeter, a density roughly 14 times higher.

The shading resources differ enormously. The GTX 590 has 512 shading units, 64 texture mapping units, and 48 ROPs. The RX 7800 XT has 3,840 shading units, 240 TMUs, and 96 ROPs. That is 7.5 times more shading units, 3.75 times more TMUs, and exactly double the ROP count. The RX 7800 XT also introduces 60 dedicated ray tracing cores, a feature absent from the Fermi architecture entirely.

Clock behavior also reflects the generational gap. The GTX 590 lists no base or boost clock in the database, only a memory clock of 854 MHz (3.4 Gbps effective). The RX 7800 XT has a base clock of 1295 MHz, a boost clock of 2430 MHz, a game clock of 2124 MHz, and memory at 2438 MHz (19.5 Gbps effective). The AMD card's boost clock is nearly double the GTX's memory speed alone.

Process node improvements drive efficiency changes. The GTX 590 has a TDP of 365 W with a suggested 750 W power supply. The RX 7800 XT draws 263 W with a suggested 600 W unit, despite delivering far more compute resources. Both cards use dual-slot cooling and dual 8-pin power connectors, but the physical dimensions differ slightly: the GTX 590 measures 279 mm long, 111 mm tall, and 40 mm wide, while the RX 7800 XT is 267 mm long, 111 mm tall, and 50 mm wide.

Interface and display output also show the age gap. The GTX 590 uses PCIe 2.0 x16 and offers 3x DVI plus 1x mini-DisplayPort. The RX 7800 XT uses PCIe 4.0 x16 and provides 1x HDMI 2.1a plus 3x DisplayPort 2.1. The newer card supports modern display standards that the Fermi part cannot.

Head-to-Head Benchmarks

The recorded data contains exactly one direct benchmark comparison between these two cards: Geekbench OpenCL. In that test, the RX 7800 XT scored 18290, while the GTX 590 scored 12830. The delta of -29.9% indicates the AMD card outperforms the NVIDIA part by nearly a third in this compute workload. This is not a marginal victory; it is a decisive margin that reflects the fundamental architectural and process advantages of the newer GPU.

The GTX 590's score of 12830 places it near several roughly comparable parts. Its nearest rival, the AMD Radeon Pro 455, scores 12831 with a 0% delta. The AMD FirePro W5100 scores 12847 with a -0.1% delta, meaning the GTX 590 trails by one-tenth of a percent. The AMD Radeon 740M scores 12870 with a -0.3% delta, again showing the GTX 590 slightly behind. The NVIDIA GeForce GTX 670 scores 12773 with a +0.4% delta, meaning the GTX 590 leads that card by 0.4%. These tight margins indicate the GTX 590 sits at a performance plateau where small variations separate neighboring GPUs.

The RX 7800 XT's average score of 11627, however, is lower than its head-to-head OpenCL result. This discrepancy arises because the database also includes many other benchmark results for the RX 7800 XT, such as Passmark G3D at 24176, Passmark GPU Compute at 13473, and Geekbench Vulkan at 54228. These varied workloads pull the average down relative to the single OpenCL score. The GTX 590, by contrast, has only one recorded benchmark, so its average equals its OpenCL score.

The RX 7800 XT's nearest rivals in the overall database illustrate its positioning. The NVIDIA GeForce GTX 1660 scores 11680, a -0.5% delta, meaning the AMD card trails by half a percent. The AMD Radeon Pro 5500M scores 11528, a +0.9% delta, meaning the RX 7800 XT leads by nearly one percent. The NVIDIA Tesla K20c scores 11479, a +1.3% delta. The AMD Radeon RX 6500 XT scores 11842, a -1.8% delta. These comparisons show the RX 7800 XT clustered with midrange parts from several generations, despite its much higher raw specifications.

Specification Differences

The most striking differences appear in memory capacity and bandwidth. The GTX 590 offers 1536 MB, while the RX 7800 XT offers 16 GB, more than ten times the capacity. Bandwidth jumps from 164.0 GB/s to 624.1 GB/s, a 3.8-fold increase. The memory type changes from GDDR5 to GDDR6, and the bus narrows from 384-bit to 256-bit, yet the newer card still achieves far higher throughput due to faster memory clocks.

Compute throughput scales dramatically. The GTX 590 delivers 1,244.2 GFLOPS of FP32 performance. The RX 7800 XT delivers 37.32 TFLOPS FP32, which is roughly 30 times higher. The AMD card also lists FP16 at 37.32 TFLOPS with a 1:1 ratio, while the GTX 590 has no recorded FP16 capability. Pixel rate rises from 19.46 GPixel/s to 233.3 GPixel/s, and texture rate from 38.91 GTexel/s to 583.2 GTexel/s.

Power requirements tell a different story. The GTX 590 has a TDP of 365 W and suggests a 750 W power supply. The RX 7800 XT has a TDP of 263 W and suggests a 600 W unit. Despite delivering vastly more performance, the newer card consumes 102 W less under load and recommends a smaller power supply. This efficiency gain comes directly from the 5 nm process versus 40 nm.

Physical dimensions remain similar in length and height. The GTX 590 is 279 mm long, 111 mm tall, and 40 mm wide. The RX 7800 XT is 267 mm long, 111 mm tall, and 50 mm wide, making it slightly shorter but thicker. Both are dual-slot designs with identical power connector requirements of 2x 8-pin.

The transistor counts and die sizes highlight the manufacturing leap. The GTX 590 has 3,000 million transistors on 520 mm², while the RX 7800 XT has 28,100 million on 346 mm². The newer chip packs over nine times more transistors into a smaller area. The architecture names also differ: Fermi 2.0 versus RDNA 3.0, with the latter supporting DirectX 12 Ultimate and Vulkan 1.4, features absent from the older part.

The Verdict

The data points clearly toward the RX 7800 XT for nearly any modern workload. In the single head-to-head benchmark, it beats the GTX 590 by 29.9%. Its memory capacity is over ten times larger, its FP32 throughput is roughly 30 times higher, and its pixel and texture rates are an order of magnitude greater. It supports ray tracing, Vulkan, and DirectX 12 Ultimate, none of which the GTX 590 offers. It consumes less power and requires a smaller power supply, making it the more practical choice for current systems.

The GTX 590, however, still holds a niche in historical or legacy contexts. Its average benchmark score of 12830 actually exceeds the RX 7800 XT's average of 11627, though this is an artifact of the limited data available for the older card. The GTX 590's closest rivals are all low-to-midrange parts from the AMD Radeon Pro and FirePro lines plus the GTX 670, indicating it performs at a level comparable to those older workstation cards. For users running software from the early 2010s or maintaining vintage systems, the GTX 590 remains functional, but it cannot handle modern APIs or memory-intensive workloads.

The RX 7800 XT's nearest rivals include the GTX 1660, Radeon Pro 5500M, Tesla K20c, and Radeon RX 6500 XT, all within a 3% band of its average score. This clustering suggests the RX 7800 XT, despite its high specifications, lands in the midrange tier in practical database benchmarks. Its OpenCL score of 18290, however, places it well above that cluster, indicating strong compute performance in specific workloads.

Where Each One Wins

The RX 7800 XT wins in every modern compute scenario. The Geekbench OpenCL result shows a 29.9% advantage, and its Vulkan score of 54228 demonstrates strong API support that the GTX 590 cannot match due to lacking Vulkan entirely. For DirectX 12 Ultimate titles, ray tracing workloads, or applications using FP16 compute, the RX 7800 XT is the only viable option between the two. Its 16 GB memory capacity suits high-resolution textures and large datasets, while the GTX 590's 1536 MB will hit capacity limits quickly.

The GTX 590 wins only in scenarios defined by historical relevance or legacy software compatibility. Its 384-bit memory bus and 164.0 GB/s bandwidth were competitive for its era, and its 3,000 million transistor count on a 520 mm² die made it a flagship part in 2011. For users running DirectX 11-era games or OpenGL applications from that period, the GTX 590 may still perform adequately, as evidenced by its OpenCL score of 12830 matching the Radeon Pro 455. Its 48 ROPs and 64 TMUs provide enough rasterization throughput for older titles, but no modern benchmark in the database favors it.

The Passmark suite results for the RX 7800 XT show varied strengths: DirectX 9 scores 304, DirectX 11 scores 249, DirectX 12 scores 93, G2D scores 1177, G3D scores 24176, and GPU compute scores 13473. These numbers indicate the RX 7800 XT excels in general 3D rendering and compute tasks, while its DirectX 12 score is notably lower relative to its other results. The GTX 590 has no Passmark entries, so no direct comparison exists for those workloads, but the architecture gap suggests the newer card would dominate across all of them.