AMD Radeon RX 9070 XT vs NVIDIA GeForce GTX 1660 SUPER Comparison

The AMD Radeon RX 9070 XT and NVIDIA GeForce GTX 1660 SUPER represent two distant points in the GPU timeline, separated by a generation gap that is clearly visible in the benchmark data. The RX 9070 XT, built on RDNA 4.0, dominates the majority of the tested workloads, while the GTX 1660 SUPER, a Turing-era card, shows a single but notable strength in one specific compute scenario. The data shows a total of 9 benchmark wins for the AMD card against 1 for the NVIDIA card, but the margin of victory varies drastically depending on the test.

Where Each One Wins

The AMD Radeon RX 9070 XT is the clear victor in all DirectX gaming scenarios. In PassMark’s DirectX 11 test, it scores 292 against the GTX 1660 SUPER’s 104, a 180.8% advantage. The lead persists in DirectX 12, where the RX 9070 XT scores 78 versus 50, a 56% difference, and in the legacy DirectX 9 test, it wins 353 to 189 (86.8% ahead). The most extreme gaming delta appears in the 3DMark Steel Nomad DX12 benchmark, where the RX 9070 XT scores 7260 against 1278, a massive 468.1% lead. This indicates the AMD card is not just faster but in a completely different performance class for modern rasterization workloads.

The NVIDIA GeForce GTX 1660 SUPER’s sole victory comes in the Geekbench OpenCL test, where it scores 52490 against the RX 9070 XT’s 17428, a 66.8% deficit for the AMD card. This is a striking reversal, suggesting that the older card has a particular efficiency in this specific OpenCL compute workload that does not translate to other benchmarks. Outside of that single test, the NVIDIA card also trails in the Vulkan API test, scoring 57102 against the RX 9070 XT’s 65879, a 15.4% win for AMD. The PassMark G2D test, which measures 2D graphics performance, also goes to AMD (1328 vs 805, a 65% lead), and the compute-focused PassMark GPU Compute test shows AMD winning by 212.5% (15864 vs 5076).

Architecture Differences

The two cards are built on fundamentally different architectures and process nodes. The AMD RX 9070 XT uses the Navi 48 chip on a 4 nm TSMC process, while the NVIDIA GTX 1660 SUPER uses the TU116 chip on a 12 nm TSMC process. This process advantage is reflected in the transistor density: the AMD chip packs 53,900 million transistors into a 357 mm² die, yielding a density of 151.0M per mm². In contrast, the NVIDIA chip has 6,600 million transistors on a larger 284 mm² die, resulting in a density of just 23.2M per mm². The AMD card also features a newer PCIe interface, using PCIe 5.0 x16 versus the GTX 1660 SUPER’s PCIe 3.0 x16.

The memory subsystems differ significantly. The RX 9070 XT comes with 16 GB of GDDR6 memory on a 256-bit bus, delivering 644.6 GB/s of bandwidth. The GTX 1660 SUPER has 6 GB of GDDR6 on a 192-bit bus, providing 336.0 GB/s. The RX 9070 XT’s compute resources are substantially larger: it has 4096 shading units, 256 TMUs, and 128 ROPs, compared to the GTX 1660 SUPER’s 1408 shading units, 88 TMUs, and 48 ROPs. The AMD card also includes 64 ray tracing cores, a feature entirely absent from the NVIDIA card, which has no RT cores. Neither card has tensor cores listed in the data.

Power and connectivity requirements also diverge. The RX 9070 XT has a TDP of 304 W and requires a 700 W power supply, using 2x 8-pin connectors. The GTX 1660 SUPER is far more modest, with a 125 W TDP, a 300 W suggested PSU, and a single 8-pin connector. The display outputs reflect the generational gap: AMD offers 1x HDMI 2.1b and 3x DisplayPort 2.1a, while NVIDIA provides 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a. The API support also differs, with AMD supporting DirectX 12 Ultimate (12_2) and NVIDIA only DirectX 12 (12_1), though both support OpenGL 4.6 and Vulkan 1.4.

FAQ

Q: Which card has a higher average benchmark score?

A: The AMD Radeon RX 9070 XT has an average benchmark score of 13543, while the NVIDIA GeForce GTX 1660 SUPER scores 12986. The AMD card also sits at the 55th percentile of all GPUs, compared to the NVIDIA card’s 53rd percentile.

Q: Is the RX 9070 XT faster in every DirectX test?

A: Yes. The AMD card wins in PassMark DirectX 9 (353 vs 189), DirectX 10 (154 vs 65), DirectX 11 (292 vs 104), and DirectX 12 (78 vs 50). It also wins the 3DMark Steel Nomad DX12 test by a significant margin.

Q: What is the only test where the GTX 1660 SUPER wins?

A: The GTX 1660 SUPER wins the Geekbench OpenCL test, scoring 52490 against the RX 9070 XT’s 17428. This represents a 66.8% deficit for the AMD card in that specific workload.

Q: How do the memory sizes compare?

A: The RX 9070 XT has 16 GB of GDDR6 memory, which is more than double the GTX 1660 SUPER’s 6 GB. The AMD card also has a wider 256-bit bus and higher bandwidth at 644.6 GB/s versus 336.0 GB/s.

Q: Which card requires a more powerful power supply?

A: The RX 9070 XT has a TDP of 304 W and a suggested PSU of 700 W, while the GTX 1660 SUPER has a TDP of 125 W and a suggested PSU of 300 W. The AMD card also uses two 8-pin connectors instead of one.

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

A: The RX 9070 XT’s nearest rival is the AMD Radeon HD 7770M with an average score of 13536 (0.1% delta). The GTX 1660 SUPER’s nearest rival is the NVIDIA GeForce RTX 3050 Ti Mobile with an average score of 12940 (0.4% delta).

Specification Differences

The following table highlights the key differences in specifications between the two cards, based solely on the data provided.

| Specification | AMD Radeon RX 9070 XT | NVIDIA GeForce GTX 1660 SUPER |

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

| Architecture | RDNA 4.0 | Turing |

| Process Node | 4 nm | 12 nm |

| Transistors | 53,900 million | 6,600 million |

| Die Size | 357 mm² | 284 mm² |

| Base Clock | 1660 MHz | 1530 MHz |

| Boost Clock | 2970 MHz | 1785 MHz |

| Memory Size | 16 GB | 6 GB |

| Memory Bus Width | 256 bit | 192 bit |

| Memory Bandwidth | 644.6 GB/s | 336.0 GB/s |

| Shading Units | 4096 | 1408 |

| TMUs | 256 | 88 |

| ROPs | 128 | 48 |

| RT Cores | 64 | None |

| Pixel Rate | 380.2 GPixel/s | 85.68 GPixel/s |

| Texture Rate | 760.3 GTexel/s | 157.1 GTexel/s |

| FP32 Performance | 48.66 TFLOPS | 5.027 TFLOPS |

| TDP | 304 W | 125 W |

| Power Connectors | 2x 8-pin | 1x 8-pin |

| Suggested PSU | 700 W | 300 W |

| Bus Interface | PCIe 5.0 x16 | PCIe 3.0 x16 |

| Display Outputs | 1x HDMI 2.1b, 3x DisplayPort 2.1a | 1x DVI, 1x HDMI 2.0, 1x DisplayPort 1.4a |

| DirectX Support | 12 Ultimate (12_2) | 12 (12_1) |

| Production Status | Active | End-of-life |

| Launch MSRP | 599 USD | 229 USD |

Head-to-Head Benchmarks

The most striking result in the head-to-head data is the 3DMark Steel Nomad DX12 test. The RX 9070 XT scores 7260, while the GTX 1660 SUPER manages only 1278, giving AMD a 468.1% advantage. This is the largest delta in any test and underscores the generational leap in rasterization performance. The second-largest win for AMD comes in PassMark GPU Compute, where the RX 9070 XT scores 15864 against 5076, a 212.5% lead. This suggests that even in pure compute tasks, the newer architecture has a massive throughput advantage.

The PassMark DirectX 11 test shows a 180.8% win for the RX 9070 XT (292 vs 104), and the DirectX 10 test shows a 136.9% win (154 vs 65). The PassMark G3D test, which aggregates 3D graphics performance, shows the RX 9070 XT at 26795 versus 12699, a 111% lead. In the Vulkan API test, the AMD card wins by a smaller margin of 15.4% (65879 vs 57102), indicating that while the lead narrows, it remains in AMD’s favor. The PassMark DirectX 9 test (86.8% win) and G2D test (65% win) also go to AMD.

The single NVIDIA victory in Geekbench OpenCL is anomalous. The GTX 1660 SUPER scores 52490, which is 66.8% higher than the RX 9070 XT’s 17428. This result is inconsistent with the other compute tests, where AMD wins by large margins, suggesting that the OpenCL workload in this benchmark is uniquely optimized for the older Turing architecture. It does not appear to indicate overall compute superiority, as the PassMark GPU Compute test shows the opposite trend.

The Verdict

The data presents a straightforward choice for most users. The AMD Radeon RX 9070 XT is the superior card for gaming and general compute, winning 9 of 10 head-to-head benchmarks. Its advantages in DirectX 11, DirectX 12, and Vulkan are consistent and often massive, with the 3DMark Steel Nomad test showing a 468.1% gap. For anyone building a modern gaming system, the RX 9070 XT is the clear performance pick.

The NVIDIA GeForce GTX 1660 SUPER should only be considered for very specific use cases. Its single win in Geekbench OpenCL, with a score of 52490, indicates a unique strength in that particular workload. However, this advantage does not extend to other compute tests, where it loses by over 200%. The card’s lower TDP of 125 W and suggested PSU of 300 W make it a more power-efficient option, but the performance penalty is severe. Given that the GTX 1660 SUPER is end-of-life and the RX 9070 XT is active, the data strongly favors the AMD card for virtually all modern applications.