AMD Radeon RX 570 vs AMD Radeon RX 590 GME Comparison

The Verdict

The recorded data shows a clear, consistent victory for the AMD Radeon RX 590 GME across every benchmark where both cards were measured. In the three head-to-head tests, the RX 590 GME wins all three, with no wins recorded for the RX 570. The average benchmark score of the RX 590 GME is 32601, which places it in the 77th percentile of all GPUs, while the RX 570 averages 28766 and sits in the 74th percentile. The gap in average score is 3835 points, which translates to a lead of roughly 13.3% for the newer card.

The largest single victory comes in the Geekbench Vulkan test, where the RX 590 GME scores 60508 against the RX 570's 42752, a delta of 41.5%. This is a substantial margin that indicates a significant advantage in Vulkan-based workloads. The other two tests show a more moderate but still decisive edge: the 3DMark Steel Nomad DX12 test shows a 13.8% lead (1001 vs 880), and the Geekbench OpenCL test shows a 13.1% lead (36294 vs 32084).

Who should pick which? The data strongly favors the RX 590 GME for anyone prioritizing raw performance, particularly in Vulkan scenarios. The RX 570, while not winning any benchmark, still holds a position in the 74th percentile and offers a lower power draw of 150 W compared to 175 W. For users with a strict power budget or those who do not need the extra performance headroom, the RX 570 remains a viable option, but the benchmark results indicate the RX 590 GME is the faster card in every measured category.

Architecture Differences

Both cards share the same fundamental architecture: GCN 4.0, built on the Polaris 20 chip, manufactured on a 14 nm process at GlobalFoundries. Both have identical transistor counts of 5,700 million and the same die size of 232 mm², yielding the same transistor density of 24.6M per mm². They also share the same generation, Polaris (RX 500), and both are listed as end-of-life products.

The differences begin with the execution resources. The RX 590 GME has 2304 shading units, 144 texture mapping units, and 32 ROPs. The RX 570 has 2048 shading units, 128 TMUs, and the same 32 ROPs. This means the RX 590 GME has 256 more shaders and 16 more TMUs, which directly contributes to its higher fill rates. The pixel rate of the RX 590 GME is 45.44 GPixel/s versus 39.81 GPixel/s for the RX 570, and the texture rate is 204.5 GTexel/s versus 159.2 GTexel/s. The FP32 compute is also higher on the RX 590 GME at 6.543 TFLOPS compared to 5.095 TFLOPS, and the FP16 rates match the FP32 rates on both cards (1:1 ratio).

Clock speeds differ as well. The RX 590 GME has a base clock of 1257 MHz and a boost clock of 1420 MHz, while the RX 570 runs at 1168 MHz base and 1244 MHz boost. Memory speed is another differentiator: the RX 590 GME runs its GDDR5 memory at 2000 MHz (8 Gbps effective), while the RX 570 runs at 1750 MHz (7 Gbps effective). With the same 256-bit bus width, the RX 590 GME achieves 256.0 GB/s bandwidth versus 224.0 GB/s for the RX 570.

Memory capacity is a major architectural split. The RX 590 GME comes with 8 GB of GDDR5, while the RX 570 has 4 GB. Both use the same memory type and bus width, but the larger frame buffer on the RX 590 GME can be decisive in texture-heavy or high-resolution workloads. The power connectors also differ: the RX 590 GME requires a single 8-pin connector, while the RX 570 uses a single 6-pin. The TDP difference is 175 W for the RX 590 GME and 150 W for the RX 570, although both cards share the same suggested PSU rating of 450 W.

Head-to-Head Benchmarks

The three recorded head-to-head tests paint a consistent picture of RX 590 GME superiority. Starting with 3DMark Steel Nomad DX12, the RX 590 GME scores 1001 against the RX 570's 880. This is a 13.8% delta in favor of the newer card. This test reflects DX12 gaming performance, and the margin indicates a solid generational uplift within the same architecture family.

The Geekbench OpenCL test shows a similar pattern: the RX 590 GME scores 36294, while the RX 570 scores 32084. The delta here is 13.1%. OpenCL performance is often used for compute tasks, and the higher shading unit count and clock speeds on the RX 590 GME explain this advantage. The RX 570's nearest rivals in the database include the AMD Radeon RX 6800M with an average score of 28874 (a delta of -0.4% relative to the RX 570), which shows the RX 570 is positioned close to that mobile flagship in average terms.

The most striking result is in Geekbench Vulkan. The RX 590 GME posts 60508, which is 41.5% higher than the RX 570's 42752. This is a massive gap, far exceeding the differences seen in OpenCL or DX12. Vulkan is known for its low overhead and efficient multi-threading, and the combination of higher clocks and more execution units on the RX 590 GME appears to amplify its advantage in this API. For context, the RX 590 GME's nearest rivals include the AMD FirePro S9300 X2 with an average score of 32540 (only 0.2% behind the RX 590 GME), and the AMD Radeon RX 7900 GRE at 32456 (0.4% behind). This shows the RX 590 GME's average score sits in a tight cluster at that performance tier.

The RX 570, meanwhile, has nearest rivals that include the AMD Radeon RX 470 at 28996 (a delta of -0.8% from the RX 570), and the NVIDIA Quadro RTX 8000 at 28421 (1.2% behind). This indicates the RX 570 is bracketed by cards that are all within a few percent of its average score, making its position less distinctive in the overall database. The RX 590 GME, by contrast, has rivals that are also very close, but its absolute scores are higher, placing it in a higher percentile.

FAQ

Q: Which card has the higher average benchmark score?

A: The AMD Radeon RX 590 GME has an average benchmark score of 32601, while the AMD Radeon RX 570 scores 28766. The RX 590 GME leads by 3835 points.

Q: How much faster is the RX 590 GME in Vulkan?

A: In the Geekbench Vulkan test, the RX 590 GME scores 60508 versus the RX 570's 42752, a delta of 41.5%.

Q: Do both cards use the same architecture?

A: Yes, both use GCN 4.0 architecture on the Polaris 20 chip, manufactured on a 14 nm process at GlobalFoundries, with identical transistor counts and die size.

Q: What is the memory capacity difference?

A: The RX 590 GME has 8 GB of GDDR5 memory, while the RX 570 has 4 GB. Both use a 256-bit bus, but the RX 590 GME's memory runs at 2000 MHz versus 1750 MHz on the RX 570.

Q: Which card has a higher TDP?

A: The RX 590 GME has a TDP of 175 W, while the RX 570 has a TDP of 150 W. Both cards share the same suggested PSU rating of 450 W.

Q: Did the RX 570 win any benchmark in the comparison?

A: No, the RX 570 won zero benchmarks in the head-to-head tests. The RX 590 GME won all three recorded tests.

Where Each One Wins

The RX 590 GME wins in every measured benchmark category. Its dominance is most pronounced in Vulkan, where it leads by 41.5%. This makes it the clear choice for users running Vulkan-based games or applications that leverage this API heavily. The margin in DX12 (13.8%) and OpenCL (13.1%) is smaller but still decisive. For gaming at higher resolutions or with texture-heavy settings, the 8 GB frame buffer on the RX 590 GME provides a capacity advantage that the 4 GB RX 570 cannot match, even if the raw speed difference were smaller.

The RX 570's win condition is not found in the benchmark scores, but rather in its operational profile. It draws 150 W versus 175 W, and uses a 6-pin power connector instead of an 8-pin. For systems with older power supplies or limited PCIe power connectors, the RX 570 may be easier to install. Its lower TDP also means less heat output in a chassis with limited airflow. The RX 570 still holds the 74th percentile in the database, indicating it is by no means a slow card in absolute terms, but in direct comparison, it trails the RX 590 GME in every recorded metric.

For compute workloads using OpenCL, the RX 590 GME's higher shader count and clock speeds give it a 13.1% edge. For DX12 gaming, the 13.8% lead in Steel Nomad suggests a meaningful frame rate advantage in modern titles. The RX 590 GME also holds a higher percentile rank (77 versus 74), which places it in a more exclusive performance tier overall.

Specification Differences

The following specifications differ between the two cards, based on the recorded data:

• Base Clock: 1257 MHz (RX 590 GME) versus 1168 MHz (RX 570)
• Boost Clock: 1420 MHz (RX 590 GME) versus 1244 MHz (RX 570)
• Memory Clock: 2000 MHz / 8 Gbps effective (RX 590 GME) versus 1750 MHz / 7 Gbps effective (RX 570)
• Memory Size: 8 GB (RX 590 GME) versus 4 GB (RX 570)
• Memory Bandwidth: 256.0 GB/s (RX 590 GME) versus 224.0 GB/s (RX 570)
• Shading Units: 2304 (RX 590 GME) versus 2048 (RX 570)
• TMUs: 144 (RX 590 GME) versus 128 (RX 570)
• Pixel Rate: 45.44 GPixel/s (RX 590 GME) versus 39.81 GPixel/s (RX 570)
• Texture Rate: 204.5 GTexel/s (RX 590 GME) versus 159.2 GTexel/s (RX 570)
• FP32 Performance: 6.543 TFLOPS (RX 590 GME) versus 5.095 TFLOPS (RX 570)
• FP16 Performance: 6.543 TFLOPS (RX 590 GME) versus 5.095 TFLOPS (RX 570)
• TDP: 175 W (RX 590 GME) versus 150 W (RX 570)
• Power Connectors: 1x 8-pin (RX 590 GME) versus 1x 6-pin (RX 570)
• Display Outputs: 1x HDMI 2.0b, 3x DisplayPort 1.4a (RX 590 GME) versus 1x DVI, 1x HDMI 2.0b, 3x DisplayPort 1.4a (RX 570)
• Release Date: 2020-03-08 (RX 590 GME) versus 2017-04-17 (RX 570)
• Launch MSRP: The RX 570 had a launch MSRP of 169 USD; the RX 590 GME has no recorded launch MSRP.

All other specifications are identical: 14 nm process, GlobalFoundries foundry, 5,700 million transistors, 232 mm² die size, 24.6M / mm² density, 256-bit bus width, GDDR5 memory type, 32 ROPs, dual-slot width, PCIe 3.0 x16 interface, 450 W suggested PSU, DirectX 12 (12_0), OpenGL 4.6, Vulkan 1.3, 241 mm length, and end-of-life production status.