AMD Radeon RX 590 vs NVIDIA GeForce RTX 4070 Mobile Comparison

FAQ

Q: How do the NVIDIA GeForce RTX 4070 Mobile and AMD Radeon RX 590 compare in overall benchmark scores?

A: The RTX 4070 Mobile has an average benchmark score of 27,435, placing it in the 73rd percentile of all GPUs. The RX 590 has an average score of 24,744, placing it in the 70th percentile. The RTX 4070 Mobile is approximately 10.9% ahead in average score.

Q: What is the closest rival to each card according to the database?

A: The RTX 4070 Mobile's nearest rival is the AMD Radeon RX 6700 XT, with an average score of 27,425 (a 0% delta). The RX 590's nearest rival is the NVIDIA RTX A5000 Mobile, with an average score of 24,763 (a -0.1% delta).

Q: Which GPU has the higher transistor count and density?

A: The RTX 4070 Mobile uses 22,900 million transistors on a 188 mm² die, yielding a density of 121.8M transistors per mm². The RX 590 uses 5,700 million transistors on a 232 mm² die, yielding a density of 24.6M per mm². The RTX 4070 Mobile has roughly four times the transistor count.

Q: Do both cards support the same DirectX version?

A: No. The RTX 4070 Mobile supports DirectX 12 Ultimate (12_2), while the RX 590 supports DirectX 12 (12_0). The RTX 4070 Mobile also supports Vulkan 1.4 versus Vulkan 1.3 on the RX 590; both support OpenGL 4.6.

Q: What are the FP32 compute capabilities of each GPU?

A: The RTX 4070 Mobile delivers 15.62 TFLOPS of FP32 compute, while the RX 590 delivers 7.119 TFLOPS. The RTX 4070 Mobile is more than double the FP32 throughput of the RX 590.

Q: Which card has dedicated ray tracing and tensor cores?

A: Only the RTX 4070 Mobile has dedicated hardware: 36 ray tracing cores and 144 tensor cores. The RX 590 has no ray tracing cores and no tensor cores listed in the database.

Where Each One Wins

The recorded data splits the two GPUs into distinct usage profiles. The RTX 4070 Mobile dominates modern, compute-heavy workloads and API-level performance. Its Geekbench OpenCL score of 109,197 and Vulkan score of 108,367 are overwhelming leads over the RX 590's only comparable results. The RX 590, however, shows a specific strength in one test: Geekbench Metal, where it scores 48,407. The RTX 4070 Mobile has no Metal score recorded, so for Metal-based applications on Apple platforms, the RX 590 is the only one of the two with demonstrated capability.

In DirectX legacy tests, the RX 590 holds an edge. The database records a Passmark DirectX 9 score of 223 for the RX 590, while the RTX 4070 Mobile scores 116 in the same test, giving the older card a 92% advantage. For DirectX 10, the RX 590 scores 116 versus the RTX 4070 Mobile's 116, a tie. For DirectX 11, the RX 590 scores 179 versus 179, also a tie. The RTX 4070 Mobile wins DirectX 12 clearly with a Passmark score of 85 versus the RX 590's 1081 in 3DMark Steel Nomad DX12, though these are different tests and not directly comparable.

The RX 590 also wins in raw pixel throughput on older rasterization tests: its pixel rate is 49.44 GPixel/s versus 81.36 GPixel/s for the RTX 4070 Mobile, so the RTX 4070 Mobile actually wins that metric. The RX 590 wins in texture rate? No, the RTX 4070 Mobile has a higher texture rate at 244.1 GTexel/s versus 222.5 GTexel/s. The RX 590's wins are confined to legacy DirectX 9 and the Metal API, while the RTX 4070 Mobile wins every other recorded benchmark and specification category.

Architecture Differences

The architectural gap between these two GPUs is generational. The RTX 4070 Mobile is built on Ada Lovelace architecture using a 5 nm process at TSMC, while the RX 590 uses GCN 4.0 architecture on a 12 nm process at GlobalFoundries. The chip identifiers tell the story: AD106 versus Polaris 30. The RTX 4070 Mobile is from the GeForce 40 Mobile generation, succeeding the GeForce 30 Mobile series. The RX 590 belongs to the Polaris (RX 500) generation, succeeding Arctic Islands and preceding Vega.

Transistor integration differs massively. The RTX 4070 Mobile packs 22,900 million transistors into a 188 mm² die, achieving a density of 121.8M transistors per mm². The RX 590 has 5,700 million transistors on a larger 232 mm² die, with a density of just 24.6M per mm². That is a 4x transistor count advantage and a 5x density advantage for the newer card.

The RTX 4070 Mobile includes hardware features the RX 590 completely lacks: 36 ray tracing cores and 144 tensor cores. The RX 590 has no such units. The RTX 4070 Mobile also supports DirectX 12 Ultimate (12_2), while the RX 590 tops out at DirectX 12 (12_0). Vulkan support is newer on the RTX 4070 Mobile (1.4 versus 1.3). Both cards support OpenGL 4.6.

Memory technology differs: the RTX 4070 Mobile uses GDDR6 with a 128-bit bus, while the RX 590 uses GDDR5 with a 256-bit bus. Interestingly, both achieve the same memory bandwidth of 256.0 GB/s, because the RTX 4070 Mobile runs at 16 Gbps effective versus 8 Gbps effective on the RX 590. The RX 590 compensates for its older, slower memory with a wider bus.

Shader resources are heavily skewed toward the RTX 4070 Mobile: 4,608 shading units versus 2,304 on the RX 590. Both have 144 texture mapping units, but the RTX 4070 Mobile has 48 ROPs versus 32 on the RX 590. The FP32 compute of the RTX 4070 Mobile is 15.62 TFLOPS, more than double the RX 590's 7.119 TFLOPS. Both cards have identical FP16 to FP32 ratios (1:1).

Specification Differences

The two cards differ across nearly every specification field. The RTX 4070 Mobile has a base clock of 1395 MHz and a boost clock of 1695 MHz. The RX 590 has a higher base clock of 1469 MHz and a higher boost clock of 1545 MHz, so the older card runs at higher clock speeds, but the newer card's architecture and shader count make up for it.

Memory: both have 8 GB, but the RTX 4070 Mobile uses GDDR6 at 2000 MHz (16 Gbps effective) on a 128-bit bus, while the RX 590 uses GDDR5 at 2000 MHz (8 Gbps effective) on a 256-bit bus. Bandwidth is identical at 256.0 GB/s.

Power and physical design differ sharply. The RTX 4070 Mobile has a TDP of 115 W, uses an IGP slot width, and requires no power connectors. The RX 590 has a TDP of 175 W, is a dual-slot card, requires one 8-pin power connector, and has a suggested PSU of 450 W. The RX 590 measures 241 mm (9.5 inches) in length; the RTX 4070 Mobile has no recorded dimensions as it is a mobile IGP.

Bus interface: the RTX 4070 Mobile uses PCIe 4.0 x8, while the RX 590 uses PCIe 3.0 x16. Display outputs on the RX 590 are 1x HDMI 2.0b and 3x DisplayPort 1.4a; the RTX 4070 Mobile's outputs are portable device dependent.

Production status and release dates differ: the RTX 4070 Mobile is active and was released on 2023-01-02, while the RX 590 is end-of-life and was released on 2018-11-14. The RX 590 has a launch MSRP of 279 USD, mentioned once here. The RTX 4070 Mobile has no recorded launch MSRP.

Head-to-Head Benchmarks

The database has no direct head-to-head benchmark entries between these two cards, but the individual benchmark suites provide clear comparisons. The largest win for the RTX 4070 Mobile is in Geekbench OpenCL: it scores 109,197, a massive lead over the RX 590's only comparable compute score. The RX 590 has no OpenCL score recorded, so the comparison is qualitative, but the RTX 4070 Mobile's score places it in the top tier of compute performance.

In Geekbench Vulkan, the RTX 4070 Mobile scores 108,367. The RX 590 has no Vulkan score in the database. The RTX 4070 Mobile's Passmark G3D score is 19,587, which is a strong result; the RX 590 has no G3D score recorded. The RTX 4070 Mobile's Passmark GPU Compute score is 8,399; again, the RX 590 has no comparable entry.

The RX 590's recorded wins come from tests where the RTX 4070 Mobile has no data. The RX 590 scores 48,407 in Geekbench Metal, which is its strongest result. In 3DMark Steel Nomad DX12, the RX 590 scores 1,081. The RTX 4070 Mobile has no Metal or Steel Nomad results in the database.

Looking at Passmark DirectX tests where both have scores: DirectX 9 favors the RX 590 at 223 versus 116 for the RTX 4070 Mobile, a 92% advantage for the older card. DirectX 10 is a tie at 116 each. DirectX 11 is a tie at 179 each. DirectX 12 favors the RTX 4070 Mobile at 85, but the RX 590 has no DirectX 12 Passmark score; its 3DMark Steel Nomad DX12 score of 1,081 is a different test and cannot be directly compared.

Pixel and texture rates favor the RTX 4070 Mobile: 81.36 GPixel/s versus 49.44 GPixel/s (a 65% advantage), and 244.1 GTexel/s versus 222.5 GTexel/s (a 10% advantage). The RTX 4070 Mobile's FP32 throughput of 15.62 TFLOPS is more than double the RX 590's 7.119 TFLOPS.

The Verdict

The data clearly favors the NVIDIA GeForce RTX 4070 Mobile for nearly every modern workload. It has a higher average benchmark score (27,435 versus 24,744), a higher percentile ranking (73rd versus 70th), more than double the FP32 compute, dedicated ray tracing and tensor cores, and newer architecture on a more advanced process node. The RTX 4070 Mobile also matches the RX 590's memory bandwidth despite a narrower bus, and does so at a lower TDP (115 W versus 175 W) with no power connectors required.

The AMD Radeon RX 590 retains two specific advantages in the recorded data. First, it leads in legacy DirectX 9 performance, scoring 223 versus 116, a 92% advantage. Second, it has a recorded Geekbench Metal score of 48,407, while the RTX 4070 Mobile has no Metal result, making the RX 590 the only one of the two with demonstrated Apple platform support.

For users prioritizing current DirectX 12 Ultimate titles, ray tracing workloads, tensor-based compute, or any Vulkan application, the RTX 4070 Mobile is the clear choice. Its benchmark scores are consistently higher across every test where both cards have data, except for DirectX 9 and the tied DirectX 10 and DirectX 11 results. The RTX 4070 Mobile also offers superior power efficiency and a smaller physical footprint, being an IGP rather than a dual-slot card.

The RX 590, being end-of-life, is only relevant for legacy DirectX 9 titles or Metal-specific projects. Its higher TDP, dual-slot design, and required 8-pin power connector make it less practical for modern systems, but its DirectX 9 score suggests it may still handle older games with ease.

The verdict: choose the RTX 4070 Mobile for any modern workload, especially ray tracing, compute, or Vulkan. Choose the RX 590 only if you specifically need DirectX 9 performance or Metal compatibility, and if power draw and physical size are not concerns. The RTX 4070 Mobile is the superior GPU in nearly every measurable category.