AMD Radeon RX 590 vs NVIDIA GeForce RTX 3070 Ti Mobile Comparison

Head-to-Head Benchmarks

The single available head-to-head benchmark — 3DMark Steel Nomad DX12 — delivers a decisive result. The NVIDIA GeForce RTX 3070 Ti Mobile scores 2572 points, while the AMD Radeon RX 590 manages 1081 points. That is a 58% deficit for the AMD card in this test. The gap is enormous, but it is the only direct comparison available in the dataset, so broader conclusions must be drawn from the aggregate scores and the rival lists.

Looking at the average benchmark scores, the story becomes more nuanced. The RX 590 posts an average score of 24744 across its benchmark suite, which places it in the 70th percentile of all GPUs. The RTX 3070 Ti Mobile, despite winning the Steel Nomad test by a wide margin, has an average score of only 23518 and sits in the 69th percentile. This is a counterintuitive result: the NVIDIA card wins the modern DirectX 12 workload decisively, yet its overall average across all tested workloads is 5% lower than the AMD card’s average (24744 vs 23518).

The rival lists help contextualize these averages. The RX 590’s nearest rival, the NVIDIA RTX A5000 Mobile, scores 24763 — a 0.1% gap, meaning the RX 590 is statistically tied with that workstation-class mobile GPU. The Intel Arc A350M trails by 0.4%, the AMD Radeon RX 6600 XT trails by 1.2%, and the NVIDIA GeForce GTX 1630 trails by 1.9%. For a desktop card released in late 2018, this is a strong aggregate showing. The RTX 3070 Ti Mobile, by contrast, sits within 0.5% of the RTX 3080 Mobile (23628), 0.9% ahead of the AMD Radeon AI PRO R9700 (23315), 0.9% behind the GTX TITAN Z (23736), and 1% ahead of the AMD Radeon R9 M290X (23276). The mobile NVIDIA part is clustered tightly among these rivals, none of which are modern flagship parts.

The Steel Nomad result, however, cannot be dismissed. A 58% lead in a DirectX 12 test suggests that the RTX 3070 Ti Mobile has a significant architectural advantage in modern workloads, even if its average score is dragged down by older or compute-oriented tests where the RX 590’s GCN architecture remains competitive. The RX 590 also shows a Geekbench Metal score of 48407, a metric not available for the NVIDIA card, which instead posts Geekbench OpenCL (106022) and Vulkan (100027) scores. These are different APIs and not directly comparable, but the NVIDIA card’s OpenCL result is more than double the AMD card’s Metal score, hinting at substantial compute throughput differences.

In the Passmark suite, the RTX 3070 Ti Mobile shows a peculiar pattern: DirectX 9 (196), DirectX 10 (124), DirectX 11 (153), DirectX 12 (73), G2D (783), G3D (17727), and GPU compute (7504). The DirectX 12 score of 73 is strikingly low relative to its G3D score, which may reflect driver overhead or test methodology rather than raw capability. No Passmark scores exist for the RX 590 in this dataset, so no direct comparison is possible there.

Architecture Differences

The two GPUs represent fundamentally different design philosophies and manufacturing eras. The RX 590 uses the Polaris 30 chip built on GCN 4.0 architecture, fabricated on a 12 nm process at GlobalFoundries. The chip contains 5,700 million transistors on a 232 mm² die, yielding a transistor density of 24.6 million per square millimeter. The RTX 3070 Ti Mobile uses the GA104 chip built on Ampere architecture, fabricated on an 8 nm process at Samsung. It packs 17,400 million transistors on a 392 mm² die, with a density of 44.4 million per square millimeter. The transistor count is 3.05 times higher on the NVIDIA chip, and the density is 1.8 times higher, reflecting the more advanced process node.

The core configurations diverge sharply. The RX 590 has 2304 shading units, 144 texture mapping units, and 32 ROPs. The RTX 3070 Ti Mobile has 5888 shading units, 184 TMUs, and 96 ROPs. That is 2.56 times more shading units, 1.28 times more TMUs, and 3 times more ROPs. The NVIDIA card also adds dedicated hardware that the AMD card lacks entirely: 46 ray tracing cores and 184 tensor cores. These are absent from the RX 590’s specification, meaning the AMD card cannot accelerate ray tracing or AI-based features at the hardware level.

Clock speeds tell a different story. The RX 590 runs at a base of 1469 MHz and a boost of 1545 MHz, while the RTX 3070 Ti Mobile runs at a much lower base of 915 MHz and a boost of 1410 MHz. Despite the lower clocks, the NVIDIA card achieves far higher throughput because of its massive core count. The pixel rate for the RTX 3070 Ti Mobile is 135.4 GPixel/s versus 49.44 GPixel/s for the RX 590 — a 2.74 times advantage. The texture rate is 259.4 GTexel/s versus 222.5 GTexel/s, a more modest 1.17 times advantage. The FP32 compute is 16.60 TFLOPS versus 7.119 TFLOPS, a 2.33 times advantage. Both cards have a 1:1 FP16 ratio, so the FP16 figures match their FP32 numbers.

Memory configurations are similar in capacity but different in type and speed. Both have 8 GB, but the RX 590 uses GDDR5 at 2000 MHz (8 Gbps effective) on a 256-bit bus, yielding 256.0 GB/s of bandwidth. The RTX 3070 Ti Mobile uses GDDR6 at 1750 MHz (14 Gbps effective) on the same 256-bit bus, yielding 448.0 GB/s — a 1.75 times bandwidth advantage. The power profiles are inverted in an interesting way: the RX 590 has a TDP of 175 W and requires a 1x 8-pin power connector with a 450 W suggested PSU, while the RTX 3070 Ti Mobile has a TDP of 115 W and no power connectors (portable device dependent). The NVIDIA card is more power-efficient despite its higher performance in the Steel Nomad test.

Interface and API support also differ. The RX 590 uses PCIe 3.0 x16, while the RTX 3070 Ti Mobile uses PCIe 4.0 x16. The RX 590 supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.3. The RTX 3070 Ti Mobile supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The NVIDIA card’s higher DirectX feature level and newer Vulkan version reflect its more modern architecture.

The Verdict

The data presents a clear divergence between synthetic aggregate performance and modern workload performance. If the sole criterion is the 3DMark Steel Nomad DX12 result, the RTX 3070 Ti Mobile is the overwhelming winner, leading by 58%. That is a massive margin in a test that is likely representative of contemporary DirectX 12 gaming. The NVIDIA card also brings 46 ray tracing cores and 184 tensor cores, which the RX 590 cannot match at all. For any workload that uses ray tracing, DLSS, or other tensor-core features, the RX 590 is not merely slower — it is incapable of participating.

However, the aggregate benchmark average tells a different story. The RX 590’s average score of 24744 exceeds the RTX 3070 Ti Mobile’s 23518 by 5%. The RX 590 also sits in the 70th percentile versus the 69th percentile for the NVIDIA card. This suggests that across a broader set of workloads, the older GCN architecture remains competitive, likely due to strengths in compute-heavy or legacy API scenarios. The RX 590’s nearest rival is the workstation-class RTX A5000 Mobile (within 0.1%), while the RTX 3070 Ti Mobile is clustered with mid-range parts like the RTX 3080 Mobile and GTX TITAN Z.

The verdict hinges on workload relevance. For users prioritizing modern DirectX 12 gaming, ray tracing, or AI-accelerated features, the RTX 3070 Ti Mobile is the clear choice — the 58% Steel Nomad lead is decisive. For users running a diverse mix of applications where aggregate scores matter, the RX 590 holds a slight edge. The data does not support a universal winner; it supports two different winners for two different use cases. The RTX 3070 Ti Mobile is the modern performance pick, but the RX 590’s aggregate score suggests it remains a capable general-purpose GPU.

Specification Differences

| Specification | AMD Radeon RX 590 | NVIDIA GeForce RTX 3070 Ti Mobile |

|---|---|---|

| Architecture | GCN 4.0 | Ampere |

| Process node | 12 nm | 8 nm |

| Foundry | GlobalFoundries | Samsung |

| Transistors | 5,700 million | 17,400 million |

| Die size | 232 mm² | 392 mm² |

| Transistor density | 24.6M / mm² | 44.4M / mm² |

| Base clock | 1469 MHz | 915 MHz |

| Boost clock | 1545 MHz | 1410 MHz |

| Memory type | GDDR5 | GDDR6 |

| Memory clock | 2000 MHz (8 Gbps effective) | 1750 MHz (14 Gbps effective) |

| Memory bandwidth | 256.0 GB/s | 448.0 GB/s |

| Shading units | 2304 | 5888 |

| TMUs | 144 | 184 |

| ROPs | 32 | 96 |

| RT cores | None | 46 |

| Tensor cores | None | 184 |

| Pixel rate | 49.44 GPixel/s | 135.4 GPixel/s |

| Texture rate | 222.5 GTexel/s | 259.4 GTexel/s |

| FP32 / FP16 | 7.119 TFLOPS (1:1) | 16.60 TFLOPS (1:1) |

| TDP | 175 W | 115 W |

| Power connectors | 1x 8-pin | None |

| Suggested PSU | 450 W | Not specified |

| Bus interface | PCIe 3.0 x16 | PCIe 4.0 x16 |

| DirectX | 12 (12_0) | 12 Ultimate (12_2) |

| Vulkan | 1.3 | 1.4 |

| Display outputs | 1x HDMI 2.0b, 3x DisplayPort 1.4a | Portable Device Dependent |

| Form factor | Dual-slot, 241 mm (9.5 inches) | Not specified |

| Release date | 2018-11-14 | 2022-01-03 |

FAQ

Q: Which GPU has a higher average benchmark score?

A: The AMD Radeon RX 590 has an average benchmark score of 24744, which is 5% higher than the NVIDIA GeForce RTX 3070 Ti Mobile’s average of 23518.

Q: What is the performance difference in 3DMark Steel Nomad DX12?

A: The RTX 3070 Ti Mobile scores 2572, while the RX 590 scores 1081. The RTX 3070 Ti Mobile leads by 58% in this test.

Q: Does the RX 590 support ray tracing or tensor cores?

A: No. The RX 590 has no ray tracing cores and no tensor cores. The RTX 3070 Ti Mobile has 46 ray tracing cores and 184 tensor cores.

Q: How does memory bandwidth compare between the two?

A: The RX 590 has 256.0 GB/s of bandwidth with GDDR5 memory, while the RTX 3070 Ti Mobile has 448.0 GB/s with GDDR6 memory. The NVIDIA card has 1.75 times the bandwidth.

Q: Which GPU has a higher TDP?

A: The RX 590 has a TDP of 175 W, while the RTX 3070 Ti Mobile has a TDP of 115 W. The AMD card consumes more power despite being slower in the Steel Nomad test.

Q: What are the nearest rivals for each GPU based on average score?

A: The RX 590’s nearest rival is the NVIDIA RTX A5000 Mobile (24763, 0.1% gap). The RTX 3070 Ti Mobile’s nearest rival is the NVIDIA GeForce RTX 3080 Mobile (23628, 0.5% gap).

Where Each One Wins

The RTX 3070 Ti Mobile wins in modern DirectX 12 workloads. The 3DMark Steel Nomad DX12 result is the only direct head-to-head benchmark, and the NVIDIA card wins it by 58%. This is a definitive victory in a test that stresses current-generation rendering features. The NVIDIA card also wins on raw compute throughput: 16.60 TFLOPS FP32 versus 7.119 TFLOPS, and 448.0 GB/s memory bandwidth versus 256.0 GB/s. It wins on pixel rate (135.4 GPixel/s vs 49.44 GPixel/s) and texture rate (259.4 GTexel/s vs 222.5 GTexel/s). The presence of 46 RT cores and 184 tensor cores means it wins in any ray-traced or AI-accelerated workload the RX 590 simply cannot run. It also wins on power efficiency, with a 115 W TDP versus 175 W.

The RX 590 wins on aggregate benchmark performance. Its average score of 24744 exceeds the RTX 3070 Ti Mobile’s 23518, placing it in the 70th percentile versus the 69th. It wins in the context of its rival list: it is within 0.1% of the RTX A5000 Mobile, whereas the RTX 3070 Ti Mobile is within 0.5% of the RTX 3080 Mobile. The RX 590 also has a higher base clock (1469 MHz vs 915 MHz) and boost clock (1545 MHz vs 1410 MHz), which may benefit lightly threaded or latency-sensitive workloads. Its dual-slot desktop form factor with dedicated display outputs (1x HDMI 2.0b, 3x DisplayPort 1.4a) gives it an advantage in fixed desktop setups, whereas the RTX 3070 Ti Mobile’s display outputs are “portable device dependent.” The RX 590 also carries a launch MSRP of 279 USD, a fact that may inform historical context, though pricing is not a factor in performance analysis.

For users who run a broad mix of modern and legacy applications, the RX 590’s higher aggregate score suggests it holds up better across the board. For users who play the latest DirectX 12 titles or use ray tracing, the RTX 3070 Ti Mobile is the only viable option between the two. The data does not indicate a single winner — it indicates that the RTX 3070 Ti Mobile wins the modern workload, while the RX 590 wins the aggregate.