AMD Radeon RX 7800 XT vs NVIDIA GeForce GTX 1660 SUPER Comparison

NVIDIA GeForce GTX 1660 SUPER and AMD Radeon RX 7800 XT occupy different corners of the GPU landscape, separated by four years of architecture evolution. The database shows the RX 7800 XT wins 8 of 10 head-to-head benchmarks, yet the GTX 1660 SUPER takes two notable victories that reveal a more complex picture than raw performance alone. This comparison focuses on what each card does best, where the architectures diverge, and how the recorded scores translate to real workloads.

Where Each One Wins

The RX 7800 XT dominates the PassMark suite and the modern DirectX 12 stress test. In 3DMark Steel Nomad DX12, it scores 4157 against 1278 for the GTX 1660 SUPER, a delta of 69.3% in AMD's favor. That margin reflects the newer card's ability to handle current-generation rendering loads with far more headroom. The RX 7800 XT also wins every PassMark category: DirectX 10 (121 vs 65, 46.3% ahead), DirectX 11 (249 vs 104, 58.2% ahead), DirectX 12 (93 vs 50, 46.2% ahead), DirectX 9 (304 vs 189, 37.8% ahead), and the overall G3D score (24176 vs 12699, 47.5% ahead). Its compute advantage shows in PassMark GPU Compute, where it scores 13473 versus 5076, a 62.3% lead.

The GTX 1660 SUPER wins in two places: Geekbench OpenCL and Vulkan. In OpenCL, it posts 52490 against 18290, a massive 187% advantage. In Vulkan, it scores 57102 versus 54228, a narrower 5.3% edge. These wins suggest the older Turing architecture excels in certain compute and API-specific workloads, likely due to driver optimization or workload characteristics that favor its design. For users running OpenCL-based applications or Vulkan titles that leverage those paths, the GTX 1660 SUPER remains competitive despite its age.

The practical split is clear: the RX 7800 XT is built for sustained high-fidelity gaming and compute-heavy tasks, while the GTX 1660 SUPER still holds value in specific API scenarios where its architecture punches above its class.

Architecture Differences

The two GPUs come from different foundries and process nodes. The GTX 1660 SUPER uses TSMC's 12 nm process, packing 6,600 million transistors into a 284 mm² die, giving a transistor density of 23.2M per mm². The RX 7800 XT moves to TSMC's 5 nm node, housing 28,100 million transistors on a 346 mm² die, with a density of 81.2M per mm². That density increase is nearly 3.5 times, which explains the massive performance gap in most benchmarks.

Clock behavior differs fundamentally. The GTX 1660 SUPER runs a base of 1530 MHz and boosts to 1785 MHz. The RX 7800 XT has a lower base of 1295 MHz but boosts to 2430 MHz, with a game clock of 2124 MHz. The AMD card's higher boost clock, combined with its 3840 shading units versus 1408, drives its FP32 output to 37.32 TFLOPS compared to 5.027 TFLOPS. The RX 7800 XT also doubles FP16 throughput at 1:1 ratio, matching its FP32, while the GTX 1660 SUPER achieves 10.05 TFLOPS FP16 only via a 2:1 ratio.

Memory is another generational leap. The GTX 1660 SUPER uses 6 GB GDDR6 on a 192-bit bus, delivering 336.0 GB/s bandwidth. The RX 7800 XT carries 16 GB GDDR6 on a 256-bit bus, reaching 624.1 GB/s. That bandwidth difference matters for high-resolution textures and compute workloads. The RX 7800 XT also includes 60 ray tracing cores, a feature entirely absent from the GTX 1660 SUPER, which has no RT cores or tensor cores. The AMD card supports DirectX 12 Ultimate (12_2), while the NVIDIA card is limited to DirectX 12 (12_1).

Power and connectivity also diverge. The GTX 1660 SUPER is rated at 125 W TDP with a single 8-pin connector and a 300 W suggested PSU. The RX 7800 XT draws 263 W TDP, requires two 8-pin connectors, and suggests a 600 W PSU. The RX 7800 XT uses PCIe 4.0 x16, while the GTX 1660 SUPER uses PCIe 3.0 x16. Display outputs reflect the times: the older card has DVI, HDMI 2.0, and DisplayPort 1.4a; the newer one offers HDMI 2.1a and three DisplayPort 2.1 outputs.

FAQ

Q: Which card is faster in overall gaming performance?

A: The RX 7800 XT wins the PassMark G3D score decisively, 24176 versus 12699, a 47.5% lead. It also dominates DirectX 11 and DirectX 12 tests, indicating stronger performance in modern game engines.

Q: Does the GTX 1660 SUPER beat the RX 7800 XT in any benchmark?

A: Yes, it wins Geekbench OpenCL by 187% (52490 vs 18290) and Geekbench Vulkan by 5.3% (57102 vs 54228). These wins are specific to those API workloads, not typical gaming.

Q: How do the memory capacities compare?

A: The RX 7800 XT has 16 GB GDDR6 on a 256-bit bus with 624.1 GB/s bandwidth. The GTX 1660 SUPER has 6 GB GDDR6 on a 192-bit bus with 336.0 GB/s bandwidth. The RX 7800 XT offers over 2.5 times the capacity and nearly double the bandwidth.

Q: What are the power requirements for each card?

A: The GTX 1660 SUPER has a 125 W TDP with one 8-pin power connector and a suggested 300 W PSU. The RX 7800 XT has a 263 W TDP with two 8-pin connectors and a suggested 600 W PSU.

Q: Does the RX 7800 XT support ray tracing?

A: Yes, it includes 60 ray tracing cores. The GTX 1660 SUPER has no ray tracing cores or tensor cores, so it cannot perform hardware-accelerated ray tracing.

Q: Which card has better compute performance?

A: The RX 7800 XT scores 13473 in PassMark GPU Compute, 62.3% higher than the GTX 1660 SUPER's 5076. However, the GTX 1660 SUPER wins Geekbench OpenCL, showing that compute performance depends heavily on the benchmark and API used.

Specification Differences

The two cards differ in nearly every measurable specification. The GTX 1660 SUPER uses a 12 nm process with 6,600 million transistors on a 284 mm² die, while the RX 7800 XT uses 5 nm with 28,100 million transistors on a 346 mm² die. Shading units are 1408 versus 3840, texture mapping units are 88 versus 240, and ROPs are 48 versus 96. The GTX 1660 SUPER has a boost clock of 1785 MHz, while the RX 7800 XT boosts to 2430 MHz. Memory configurations are 6 GB versus 16 GB, with bus widths of 192-bit versus 256-bit. Bandwidth is 336.0 GB/s versus 624.1 GB/s. The RX 7800 XT adds 60 ray tracing cores, which the GTX 1660 SUPER lacks entirely. Pixel rate is 85.68 GPixel/s versus 233.3 GPixel/s, and texture rate is 157.1 GTexel/s versus 583.2 GTexel/s. FP32 compute is 5.027 TFLOPS versus 37.32 TFLOPS. Power draw is 125 W versus 263 W, with different power connector requirements and suggested PSU ratings. The bus interface changes from PCIe 3.0 x16 to PCIe 4.0 x16. Display outputs shift from DVI/HDMI 2.0/DisplayPort 1.4a to HDMI 2.1a/DisplayPort 2.1. Production status is end-of-life for the GTX 1660 SUPER, while the RX 7800 XT remains active.

Head-to-Head Benchmarks

The largest single victory for the RX 7800 XT comes in 3DMark Steel Nomad DX12, where it scores 4157 against 1278, a 69.3% margin. This test stresses modern DirectX 12 features, and the AMD card's architecture handles them with ease. PassMark GPU Compute shows a similar story: 13473 versus 5076, a 62.3% lead for AMD. This indicates the RX 7800 XT is significantly stronger for compute-heavy workloads like rendering or machine learning tasks.

The GTX 1660 SUPER's biggest win is Geekbench OpenCL, where it scores 52490 versus 18290, a 187% advantage. That number is striking because it reverses the expected order, suggesting the NVIDIA card has a particular strength in OpenCL execution. In Geekbench Vulkan, the GTX 1660 SUPER edges ahead with 57102 versus 54228, a 5.3% lead. These two wins show that the older card is not obsolete in all API environments.

The PassMark suite shows consistent AMD dominance. DirectX 11 is the closest large margin: 249 versus 104, a 58.2% lead. DirectX 10 gives 121 versus 65, a 46.3% lead. DirectX 12 gives 93 versus 50, a 46.2% lead. DirectX 9 gives 304 versus 189, a 37.8% lead. The overall G3D score is 24176 versus 12699, a 47.5% lead. Even the 2D test, PassMark G2D, favors AMD at 1177 versus 805, a 31.6% margin.

The data shows a clear pattern: the RX 7800 XT wins every modern and legacy gaming benchmark by substantial margins, while the GTX 1660 SUPER retains two API-specific victories that keep it relevant for particular use cases. The 8-2 win split in favor of the RX 7800 XT underscores its generational advantage, but the Geekbench results caution against dismissing the older card outright. Users targeting OpenCL or Vulkan workloads may find the GTX 1660 SUPER adequate, while those seeking maximum gaming and compute throughput should look to the RX 7800 XT.