AMD Radeon RX 590 vs NVIDIA GeForce RTX 3070 Mobile Comparison

The AMD Radeon RX 590 and the NVIDIA GeForce RTX 3070 Mobile occupy different corners of the graphics hardware landscape, one a desktop card from the Polaris generation and the other a mobile part from the Ampere generation. The database shows a clear statistical separation between the two, though the RX 590 holds a higher percentile ranking against all GPUs. The RTX 3070 Mobile records an average benchmark score of 20534, while the RX 590 posts a significantly higher average of 24744. This discrepancy, combined with a 70th percentile for the AMD card versus a 65th percentile for the NVIDIA card, suggests that the RX 590 benefits from a broader set of favorable benchmark results, while the RTX 3070 Mobile’s modern feature set is not fully captured by the aggregate score.

Where Each One Wins

The benchmark results in the database show the NVIDIA GeForce RTX 3070 Mobile winning the only direct head-to-head comparison recorded, the 3DMark Steel Nomad DX12 test. In that test, the RTX 3070 Mobile scores 2380, while the AMD Radeon RX 590 scores 1081. The delta is 54.6 percent in favor of the NVIDIA card, meaning the RTX 3070 Mobile delivers more than double the performance in this specific DirectX 12 workload. This is a decisive win for the mobile GPU in a modern, API-heavy scenario, and it reflects the architectural advantages of the Ampere design in compute-heavy rendering tasks.

However, the RX 590 wins in the aggregate metrics. Its average benchmark score of 24744 is 20.4 percent higher than the RTX 3070 Mobile’s 20534. The RX 590 also holds a better percentile position, ranking at the 70th percentile against all GPUs, while the RTX 3070 Mobile sits at the 65th percentile. This indicates that, despite losing the single head-to-head test, the RX 590 performs more consistently across the broader benchmark suite tracked by the database. The AMD card also demonstrates strong results in legacy and compute-oriented tests, such as a Geekbench Metal score of 48407, which is the only other benchmark recorded for it. The RTX 3070 Mobile, in contrast, has a wider array of scores, including a Passmark G3D score of 15309 and a Passmark GPU Compute score of 6827, but these do not boost its average above the RX 590’s.

The use-case split is therefore clear. For users focused on a single modern DirectX 12 benchmark, the RTX 3070 Mobile is the superior choice, with a score that is more than double the RX 590’s. For users who rely on the broader set of metrics tracked by the database, including Metal, OpenCL, Vulkan, and various Passmark tests, the RX 590 emerges as the stronger all-around performer. The data does not support a single winner across all categories; instead, it shows a trade-off between modern API efficiency and aggregate versatility.

The Verdict

The choice between these two GPUs depends entirely on the workload. The database shows the RTX 3070 Mobile winning the head-to-head 3DMark Steel Nomad DX12 test by a wide margin, with a score of 2380 versus 1081, a 54.6 percent advantage. This makes it the clear pick for users who prioritize performance in that specific DirectX 12 benchmark. The RTX 3070 Mobile also brings features that the RX 590 lacks, such as 40 ray tracing cores and 160 tensor cores, which are not present in the AMD card at all. These features, combined with support for DirectX 12 Ultimate (12_2) and Vulkan 1.4, position the NVIDIA card as the more future-proof option for applications that leverage these APIs.

On the other hand, the RX 590 holds a higher average benchmark score of 24744, which is 20.4 percent above the RTX 3070 Mobile’s 20534. It also ranks at the 70th percentile versus the 65th percentile for the NVIDIA card. This suggests that, across the full spectrum of tests in the database, the RX 590 delivers more consistent performance. Its nearest rivals in the database, including the NVIDIA RTX A5000 Mobile with an average score of 24763 and a delta of 0.1 percent, reinforce that the RX 590 sits in competitive company. The RTX 3070 Mobile’s nearest rivals, such as the Intel Arc B570 with an average of 20556 and a delta of 0.1 percent, are lower-performing by comparison, which further highlights the gap in average scores.

The verdict is that neither card is universally superior. The RTX 3070 Mobile wins the modern DirectX 12 test by a substantial margin and offers hardware features that the RX 590 cannot match, including ray tracing and tensor cores. The RX 590, however, wins the aggregate benchmark score and percentile ranking, making it the better choice for users who value consistent performance across a wide range of tests. The data does not indicate that one card is obsolete or dominant; it indicates a divergence in strengths that users must weigh according to their needs.

Head-to-Head Benchmarks

The only direct head-to-head benchmark in the database is the 3DMark Steel Nomad DX12 test, and it is a decisive win for the NVIDIA GeForce RTX 3070 Mobile. The RTX 3070 Mobile scores 2380, while the AMD Radeon RX 590 scores 1081, resulting in a delta of 54.6 percent in favor of the NVIDIA card. This is not a marginal difference; the RTX 3070 Mobile more than doubles the RX 590’s score. The result aligns with the architectural differences between the two cards, as the RTX 3070 Mobile features 5120 shading units, 160 texture mapping units, and 80 render output units, all of which are higher than the RX 590’s 2304 shading units, 144 TMUs, and 32 ROPs. The NVIDIA card also has a higher texture rate of 249.6 GTexel/s and a pixel rate of 124.8 GPixel/s, compared to the RX 590’s 222.5 GTexel/s and 49.44 GPixel/s.

Beyond the head-to-head, the database shows the RX 590 winning in other metrics. Its Geekbench Metal score of 48407 is the only other benchmark recorded for the AMD card, but it contributes to an average benchmark score of 24744. The RTX 3070 Mobile’s benchmarks include a Geekbench OpenCL score of 92939, a Geekbench Vulkan score of 86768, and a Passmark G3D score of 15309, among others. Despite these strong individual numbers, the RTX 3070 Mobile’s average score of 20534 falls below the RX 590’s average. This is because the RX 590’s scores are fewer but higher, while the RTX 3070 Mobile has more scores, some of which are lower, such as the Passmark DirectX 12 score of 64 and the Passmark DirectX 10 score of 113.

The pattern in the data is that the RTX 3070 Mobile wins where it directly competes with the RX 590 in a modern DirectX 12 test, but the RX 590 wins in the aggregate. The RTX 3070 Mobile’s nearest rivals, including the Intel Arc B570 with a delta of 0.1 percent and the NVIDIA Quadro M4000M with a delta of 0.3 percent, all have average scores near 20500, which is well below the RX 590’s nearest rivals. The RX 590’s nearest rivals, such as the NVIDIA RTX A5000 Mobile with an average of 24763 and the AMD Radeon RX 6600 XT with an average of 24442, are all within 2 percent of the RX 590’s average, indicating that the RX 590 is grouped with higher-performing cards.

FAQ

Q: Which GPU wins the only direct benchmark comparison in the database?

A: The NVIDIA GeForce RTX 3070 Mobile wins the 3DMark Steel Nomad DX12 test with a score of 2380, compared to the AMD Radeon RX 590’s 1081, a delta of 54.6 percent.

Q: How do the average benchmark scores compare between the two GPUs?

A: The AMD Radeon RX 590 has an average benchmark score of 24744, which is 20.4 percent higher than the NVIDIA GeForce RTX 3070 Mobile’s average of 20534.

Q: What is the percentile ranking of each GPU against all GPUs?

A: The AMD Radeon RX 590 ranks at the 70th percentile, while the NVIDIA GeForce RTX 3070 Mobile ranks at the 65th percentile.

Q: Does the RTX 3070 Mobile have any hardware features that the RX 590 lacks?

A: Yes, the RTX 3070 Mobile includes 40 ray tracing cores and 160 tensor cores, while the RX 590 has no ray tracing or tensor cores listed.

Q: What are the nearest rivals for each GPU in the database?

A: The RX 590’s nearest rival is the NVIDIA RTX A5000 Mobile with an average score of 24763 and a delta of 0.1 percent. The RTX 3070 Mobile’s nearest rival is the Intel Arc B570 with an average score of 20556 and a delta of 0.1 percent.

Q: Which GPU supports a newer version of DirectX?

A: The NVIDIA GeForce RTX 3070 Mobile supports DirectX 12 Ultimate (12_2), while the AMD Radeon RX 590 supports DirectX 12 (12_0).

Architecture Differences

The two GPUs are built on fundamentally different architectures. The AMD Radeon RX 590 uses the Polaris 30 chip, based on the GCN 4.0 architecture, and is fabricated on a 12 nm process at GlobalFoundries. The NVIDIA GeForce RTX 3070 Mobile uses the GA104 chip, based on the Ampere architecture, and is fabricated on an 8 nm process at Samsung. The process node difference is significant: the RTX 3070 Mobile’s 8 nm node is smaller, which allows for a much higher transistor count. The RTX 3070 Mobile has 17,400 million transistors on a die size of 392 mm², giving it a transistor density of 44.4 million per mm². The RX 590, by contrast, has 5,700 million transistors on a 232 mm² die, with a density of 24.6 million per mm². This means the RTX 3070 Mobile packs more than three times the transistors into a die that is only about 69 percent larger.

The compute resources also differ markedly. The RX 590 has 2304 shading units, 144 texture mapping units, and 32 render output units. The RTX 3070 Mobile has 5120 shading units, 160 TMUs, and 80 ROPs. The RTX 3070 Mobile also includes 40 ray tracing cores and 160 tensor cores, which are entirely absent from the RX 590. These additions enable hardware-accelerated ray tracing and AI-based features, which the RX 590 cannot perform at the hardware level. The FP32 performance reflects this gap: the RTX 3070 Mobile delivers 15.97 TFLOPS, while the RX 590 delivers 7.119 TFLOPS. Both cards offer FP16 performance at a 1:1 ratio with FP32.

Memory architecture is another point of divergence. The RX 590 uses 8 GB of GDDR5 memory on a 256-bit bus, with a bandwidth of 256.0 GB/s and a memory clock of 2000 MHz, or 8 Gbps effective. The RTX 3070 Mobile uses 8 GB of GDDR6 memory on a 256-bit bus, with a bandwidth of 448.0 GB/s and a memory clock of 1750 MHz, or 14 Gbps effective. The higher bandwidth of the RTX 3070 Mobile is a direct result of the faster GDDR6 memory. The RTX 3070 Mobile also supports PCIe 4.0 x16, while the RX 590 is limited to PCIe 3.0 x16.

API support differs as well. The RTX 3070 Mobile supports DirectX 12 Ultimate (12_2), Vulkan 1.4, and OpenGL 4.6. The RX 590 supports DirectX 12 (12_0), Vulkan 1.3, and OpenGL 4.6. The newer DirectX version on the NVIDIA card aligns with its ray tracing and mesh shading capabilities, which are part of the DirectX 12 Ultimate feature set. The RTX 3070 Mobile’s display outputs are listed as portable device dependent, reflecting its mobile nature, while the RX 590 offers 1x HDMI 2.0b and 3x DisplayPort 1.4a.

Specification Differences

The specification sheets for the two GPUs reveal several direct differences. The process node is 12 nm for the RX 590 and 8 nm for the RTX 3070 Mobile. The transistor count is 5,700 million for the AMD card and 17,400 million for the NVIDIA card. Die size is 232 mm² for the RX 590 and 392 mm² for the RTX 3070 Mobile, with transistor densities of 24.6 million per mm² and 44.4 million per mm², respectively.

Clock speeds differ in their configuration. The RX 590 has a base clock of 1469 MHz and a boost clock of 1545 MHz. The RTX 3070 Mobile has a base clock of 1110 MHz and a boost clock of 1560 MHz. The memory clocks are 2000 MHz with 8 Gbps effective for the RX 590, and 1750 MHz with 14 Gbps effective for the RTX 3070 Mobile. Memory type is GDDR5 for the AMD card and GDDR6 for the NVIDIA card, with both using a 256-bit bus. Memory size is 8 GB for both, but bandwidth differs: 256.0 GB/s for the RX 590 and 448.0 GB/s for the RTX 3070 Mobile.

Compute unit counts are distinct: the RX 590 has 2304 shading units, 144 TMUs, and 32 ROPs, while the RTX 3070 Mobile has 5120 shading units, 160 TMUs, and 80 ROPs. The RTX 3070 Mobile additionally has 40 ray tracing cores and 160 tensor cores, which the RX 590 does not have. Pixel rates are 49.44 GPixel/s for the RX 590 and 124.8 GPixel/s for the RTX 3070 Mobile. Texture rates are 222.5 GTexel/s and 249.6 GTexel/s, respectively. FP32 performance is 7.119 TFLOPS for the RX 590 and 15.97 TFLOPS for the RTX 3070 Mobile, with both offering FP16 at a 1:1 ratio.

Power characteristics differ substantially. The RX 590 has a TDP of 175 W, requires a 1x 8-pin power connector, and suggests a 450 W PSU. The RTX 590 has a TDP of 115 W, requires no power connectors, and has no suggested PSU listed. Bus interface is PCIe 3.0 x16 for the RX 590 and PCIe 4.0 x16 for the RTX 3070 Mobile. The RX 590 is a dual-slot card with a length of 241 mm, or 9.5 inches, while the RTX 3070 Mobile has no slot width or dimensions listed. Display outputs are 1x HDMI 2.0b and 3x DisplayPort 1.4a for the RX 590, and portable device dependent for the RTX 3070 Mobile. The RX 590 has a launch MSRP of 279 USD, while the RTX 3070 Mobile has no launch MSRP recorded. The RX 590 was released on 2018-11-14, with a predecessor of Arctic Islands and a successor of Vega. The RTX 3070 Mobile was released on 2021-01-11, with a predecessor of GeForce 20 Mobile and no successor listed. Both are end-of-life in production status.