AMD Radeon RX 590 vs NVIDIA GeForce RTX 2080 Comparison

# NVIDIA GeForce RTX 2080 vs AMD Radeon RX 590

The NVIDIA GeForce RTX 2080 and AMD Radeon RX 590 occupy very different positions in the GPU landscape, despite both being 12 nm parts from the same era. The RTX 2080 is a high-end Turing architecture card aimed at 4K and ray tracing workloads, while the RX 590 is a mid-range Polaris refresh targeting 1080p gaming. The benchmark data shows the RTX 2080 winning the only shared test decisively, but the RX 590 actually holds a higher average benchmark score across its available tests. This creates an interesting dynamic where the two cards appeal to completely different use cases, and the data reflects that split clearly.

Where Each One Wins

The RTX 2080 wins the only directly comparable benchmark, the 3DMark Steel Nomad DX12 test, with a score of 1752 versus the RX 590's 1081. That is a 62.1% advantage for the RTX 2080, a massive gap that places the two cards in entirely different performance tiers for modern DirectX 12 workloads. The RTX 2080 also posts strong scores in Geekbench Vulkan (107797) and OpenCL (91313), though the RX 590 has no comparable Geekbench results to measure against. The RTX 2080's PassMark G3D score of 18720 and GPU compute score of 7872 further demonstrate its compute-oriented strength.

The RX 590, however, wins in the aggregate. Its average benchmark score of 24744 exceeds the RTX 2080's 22895, and it holds a higher percentile ranking among all GPUs at 70 versus 68 for the RTX 2080. The RX 590's nearest rivals include the NVIDIA RTX A5000 Mobile (deltaPct -0.1), Intel Arc A350M (deltaPct 0.4), AMD Radeon RX 6600 XT (deltaPct 1.2), and NVIDIA GeForce GTX 1630 (deltaPct 1.9). This suggests the RX 590 competes in a dense mid-range field where small score differences separate many cards. The RTX 2080's nearest rivals include the Intel Arc B580 (deltaPct -0.5), AMD Radeon RX 580 2048SP (deltaPct -0.7), NVIDIA GeForce RTX 4060 Mobile (deltaPct 0.7), and NVIDIA GeForce RTX 3080 (deltaPct -1.2), showing it sits near faster modern parts despite its age.

For use-case splits, the data indicates the RTX 2080 is the choice for DX12 gaming and Vulkan workloads, while the RX 590's higher average score suggests it may excel in a broader set of legacy or mixed workloads. The RTX 2080's compute capabilities, including 46 RT cores and 368 tensor cores, point to ray tracing and AI-accelerated tasks, while the RX 590's simpler GCN architecture targets traditional rasterization.

Architecture Differences

The RTX 2080 uses the TU104 chip built on NVIDIA's Turing architecture, fabricated by TSMC on a 12 nm process. It packs 13,600 million transistors into a 545 mm² die, yielding a transistor density of 25.0M per mm². The RX 590 uses the Polaris 30 chip with GCN 4.0 architecture, built by GlobalFoundries also on 12 nm, but with just 5,700 million transistors on a 232 mm² die (24.6M per mm²). The RTX 2080's die is more than twice the size and contains well over twice the transistors, reflecting its higher complexity and feature set.

Architecturally, the RTX 2080 introduces dedicated ray tracing cores (46 of them) and tensor cores (368) that the RX 590 completely lacks. This is the fundamental feature divide: the RTX 2080 supports hardware-accelerated ray tracing and AI-enhanced features, while the RX 590 relies purely on conventional shader processing. The RTX 2080 also supports DirectX 12 Ultimate (12_2) and Vulkan 1.4, while the RX 590 is limited to DirectX 12 (12_0) and Vulkan 1.3. Both cards support OpenGL 4.6, but the API feature level difference matters for modern games and applications.

The memory subsystems also diverge. The RTX 2080 uses 8 GB of GDDR6 at 1750 MHz (14 Gbps effective) for 448.0 GB/s bandwidth, while the RX 590 uses 8 GB of GDDR5 at 2000 MHz (8 Gbps effective) for 256.0 GB/s. That is a 75% bandwidth advantage for the RTX 2080. The FP16 compute also differs significantly: the RTX 2080 delivers 20.14 TFLOPS FP16 (2:1 ratio) versus the RX 590's 7.119 TFLOPS FP16 (1:1 ratio), meaning the RTX 2080 can double its FP32 throughput when using FP16 instructions, while the RX 590 cannot.

Head-to-Head Benchmarks

The single head-to-head benchmark available is 3DMark Steel Nomad DX12, and it is a decisive win for the RTX 2080. The RTX 2080 scores 1752 against the RX 590's 1081, a delta of 62.1%. This is not a marginal victory; it is a generational leap in performance for this DirectX 12 workload. Steel Nomad is a demanding modern test that stresses overall GPU throughput, memory bandwidth, and driver efficiency, and the RTX 2080's superior specifications translate directly into a commanding lead.

The RTX 2080's wider memory bus (256-bit with GDDR6 at 448.0 GB/s) versus the RX 590's same 256-bit bus but slower GDDR5 (256.0 GB/s) likely contributes heavily to this result. The RTX 2080 also has more shading units (2944 vs 2304), more TMUs (184 vs 144), and double the ROPs (64 vs 32). Its pixel rate of 109.4 GPixel/s is more than double the RX 590's 49.44 GPixel/s, and its texture rate of 314.6 GTexel/s exceeds the RX 590's 222.5 GTexel/s. The FP32 compute of 10.07 TFLOPS versus 7.119 TFLOPS gives the RTX 2080 a 41% raw compute advantage.

Beyond the head-to-head, the RTX 2080's Geekbench Vulkan score of 107797 and OpenCL score of 91313 indicate strong cross-API performance, while the RX 590's only additional benchmark is Geekbench Metal at 48407, which has no comparable RTX 2080 result. The PassMark suite shows the RTX 2080 scoring 18720 in G3D and 7872 in GPU compute, with lower scores in older DirectX tests (136 in DX10, 158 in DX11, 72 in DX12, 223 in DX9) that suggest its driver overhead in legacy APIs. The RX 590 lacks PassMark results entirely in the data, so no comparison is possible there.

Specification Differences

The two cards differ on nearly every specification that matters for performance and features. The RTX 2080 has a base clock of 1515 MHz and boost clock of 1710 MHz, while the RX 590 runs at 1469 MHz base and 1545 MHz boost. The RTX 2080's memory clock is 1750 MHz (14 Gbps effective) versus the RX 590's 2000 MHz (8 Gbps effective), with the RTX 2080 achieving 448.0 GB/s bandwidth versus 256.0 GB/s. Both have 8 GB of memory, but the RTX 2080 uses GDDR6 while the RX 590 uses GDDR5.

Shading units differ at 2944 for the RTX 2080 versus 2304 for the RX 590. TMUs are 184 versus 144, and ROPs are 64 versus 32. The RTX 2080 includes 46 RT cores and 368 tensor cores; the RX 590 has neither. Pixel rate is 109.4 GPixel/s versus 49.44 GPixel/s, and texture rate is 314.6 GTexel/s versus 222.5 GTexel/s. FP32 is 10.07 TFLOPS versus 7.119 TFLOPS, and FP16 is 20.14 TFLOPS (2:1) versus 7.119 TFLOPS (1:1).

Power requirements also differ: the RTX 2080 has a TDP of 215 W with a suggested 550 W PSU and uses 1x 6-pin + 1x 8-pin connectors, while the RX 590 has a 175 W TDP with a suggested 450 W PSU and a single 8-pin connector. The RTX 2080 is longer at 267 mm (10.5 inches) versus the RX 590's 241 mm (9.5 inches), and the RTX 2080 adds a USB Type-C display output alongside 1x HDMI 2.0 and 3x DisplayPort 1.4a, while the RX 590 offers 1x HDMI 2.0b and 3x DisplayPort 1.4a without USB-C. Both are dual-slot cards with PCIe 3.0 x16 interfaces. The RTX 2080 was released on 2018-09-19 with a launch MSRP of 699 USD; the RX 590 followed on 2018-11-14 with a launch MSRP of 279 USD.

FAQ

Q: Which card is faster in DirectX 12 gaming?

A: The RTX 2080 wins the 3DMark Steel Nomad DX12 test with a score of 1752 versus the RX 590's 1081, a 62.1% advantage.

Q: Does the RX 590 have ray tracing support?

A: No. The RX 590 has no RT cores and supports DirectX 12 (12_0), while the RTX 2080 includes 46 RT cores and supports DirectX 12 Ultimate (12_2).

Q: Why does the RX 590 have a higher average benchmark score?

A: The RX 590's average benchmark score is 24744 across its two available tests (3DMark Steel Nomad and Geekbench Metal), while the RTX 2080 averages 22895 across ten tests including multiple PassMark and Geekbench results. The different test suites explain the discrepancy.

Q: What memory technology does each card use?

A: The RTX 2080 uses 8 GB of GDDR6 at 14 Gbps effective for 448.0 GB/s bandwidth. The RX 590 uses 8 GB of GDDR5 at 8 Gbps effective for 256.0 GB/s bandwidth.

Q: Which card requires more power?

A: The RTX 2080 has a 215 W TDP and needs a 550 W PSU with 1x 6-pin + 1x 8-pin connectors. The RX 590 has a 175 W TDP and needs a 450 W PSU with a single 8-pin connector.

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

A: The RTX 2080 delivers 10.07 TFLOPS FP32 and 20.14 TFLOPS FP16 (2:1), while the RX 590 delivers 7.119 TFLOPS FP32 and 7.119 TFLOPS FP16 (1:1). The RTX 2080 also has 368 tensor cores for AI workloads.

The Verdict

The data clearly separates these two cards by use case. The RTX 2080 is the definitive choice for modern DirectX 12 gaming and any workload that benefits from ray tracing, tensor cores, or high memory bandwidth. Its 62.1% lead in the Steel Nomad benchmark is overwhelming, and its 448.0 GB/s bandwidth, 10.07 TFLOPS FP32, and 64 ROPs place it in a higher performance tier entirely. Gamers targeting high refresh rates at 1440p or entry-level 4K should look to the RTX 2080, as should users running Vulkan applications where its 107797 Geekbench score demonstrates strength.

The RX 590, despite its lower raw specifications, posts a higher average benchmark score (24744 vs 22895) and a higher percentile ranking (70 vs 68). This suggests it performs well in the specific tests it was measured on, particularly Geekbench Metal where it scores 48407. The RX 590's lower TDP (175 W vs 215 W) and simpler power requirements make it easier to integrate into existing systems, and its shorter 241 mm length fits smaller cases. For users on a 450 W PSU or those who prioritize compatibility and efficiency over peak performance, the RX 590 remains a viable option.

The architecture gap is the deciding factor. The RTX 2080's Turing architecture with dedicated RT and tensor cores is fundamentally more capable for future-facing workloads, while the RX 590's GCN 4.0 design is a mature, proven rasterizer without hardware acceleration for newer features. If the workload is modern DX12 or Vulkan, take the RTX 2080. If the workload is legacy APIs, Metal, or the user simply needs a capable 1080p card with lower system requirements, the RX 590's higher average score and better percentile make it a reasonable pick — but the data shows the RTX 2080 is the stronger card where it matters most.