AMD Radeon Pro 555X vs NVIDIA GeForce GTX 1660 SUPER Comparison

The AMD Radeon Pro 555X is a mobile workstation part built for 2018-era Macs, while the NVIDIA GeForce GTX 1660 SUPER is a desktop gaming card from 2019. The benchmark data shows a complete mismatch in raw performance, with the GTX 1660 SUPER winning both shared tests by massive margins. This comparison is less about close competition and more about understanding what each card is designed to do.

Where Each One Wins

The AMD Radeon Pro 555X wins nowhere in the shared benchmark suite. It has zero wins across the head-to-head tests, which include Geekbench OpenCL and Geekbench Vulkan. The data shows it trailing the GTX 1660 SUPER by 75.9% in OpenCL and 77.5% in Vulkan. Its average benchmark score of 13321 places it at the 54th percentile of all GPUs, putting it in the same performance tier as the NVIDIA GeForce GTX 480 (0.2% faster), AMD FirePro M6100 (0.2% faster), AMD Radeon RX 5500M (0.3% faster), and AMD Radeon HD 8950M (0.4% faster). This is entry-level discrete performance by modern standards.

The NVIDIA GeForce GTX 1660 SUPER wins both head-to-head benchmarks decisively. Its Geekbench OpenCL score of 52490 is more than four times the Radeon Pro 555X's 12628. Its Geekbench Vulkan score of 57102 dwarfs the AMD card's 12855. The GTX 1660 SUPER's average benchmark score of 12986 is ironically lower than the Radeon Pro 555X's 13321 average, but this is because the NVIDIA card's average includes a wider range of tests, including PassMark DirectX scores that drag it down. Its percentile rank of 53% is nearly identical to the AMD card's 54%, but the head-to-head results tell the real story. The GTX 1660 SUPER sits alongside the NVIDIA GeForce RTX 3050 Ti Mobile (0.4% faster), AMD Radeon RX 580 (0.4% faster), NVIDIA Tesla M2090 (0.7% faster), and AMD Radeon 740M (0.9% faster) in overall average score.

The Verdict

The data is unambiguous: the NVIDIA GeForce GTX 1660 SUPER is the superior performer in every shared benchmark. If you are choosing between these two for any application that uses OpenCL or Vulkan, the GTX 1660 SUPER is the only rational pick. The 75.9% lead in OpenCL and 77.5% lead in Vulkan represent generational leaps in compute capability, not marginal improvements. The GTX 1660 SUPER's 5.027 TFLOPS of FP32 performance compared to the Radeon Pro 555X's 1,393.2 GFLOPS confirms this gap.

However, the Radeon Pro 555X is not without its place. Its 75W TDP and IGP slot width mean it is designed for integrated laptop use, specifically the Radeon Pro Mac (500X Series) generation. It requires no power connectors and has portable-device-dependent display outputs. If you are maintaining or repairing a 2018-era MacBook Pro, this is the card you need. The GTX 1660 SUPER, with its 125W TDP, dual-slot design, and 1x 8-pin power connector, is a desktop-only card that will not fit in that context.

The production status of both cards is end-of-life, so neither is a future-proof purchase. For a desktop builder, the choice is obvious: the GTX 1660 SUPER offers roughly four times the OpenCL performance and a 336.0 GB/s memory bandwidth versus the Radeon's 94.08 GB/s. For a Mac user with a specific socket, the Radeon Pro 555X is the only option that fits. The data does not support any scenario where the Radeon Pro 555X wins on performance.

Head-to-Head Benchmarks

The Geekbench OpenCL test shows the most extreme gap. The GTX 1660 SUPER scores 52490 against the Radeon Pro 555X's 12628, a difference of -75.9% from the AMD card's perspective. This means the NVIDIA card is roughly 4.16 times faster. The GTX 1660 SUPER's 1408 shading units and 88 texture mapping units are nearly double the Radeon's 768 and 48, respectively. The Radeon's 16 ROPs are a third of the NVIDIA card's 48. These hardware differences translate directly into the compute benchmark results.

The Geekbench Vulkan test shows a similar story. The GTX 1660 SUPER scores 57102, while the Radeon Pro 555X manages only 12855, a -77.5% delta. This is the larger percentage gap of the two tests. The Vulkan API support differs as well, with the GTX 1660 SUPER supporting Vulkan 1.4 versus the Radeon's 1.3. This newer API version may contribute to the NVIDIA card's efficiency in this workload. The GTX 1660 SUPER's pixel rate of 85.68 GPixel/s and texture rate of 157.1 GTexel/s are far ahead of the Radeon's 14.51 GPixel/s and 43.54 GTexel/s.

The average benchmark scores tell a more nuanced story. The Radeon Pro 555X's 13321 average is actually higher than the GTX 1660 SUPER's 12986. This is because the Radeon's average is based on only three Geekbench tests (Metal, OpenCL, Vulkan), all of which are compute-oriented. The GTX 1660 SUPER's average includes ten tests, several of which are PassMark DirectX 9, 10, 11, and 12 tests that score very low (189, 65, 104, and 50, respectively). These legacy DirectX tests are not representative of modern gaming performance but they pull down the NVIDIA card's average. The PassMark G3D score of 12699 for the GTX 1660 SUPER is much more indicative of its gaming capability.

FAQ

Q: Which card is faster in Geekbench OpenCL?

A: The NVIDIA GeForce GTX 1660 SUPER scores 52490, which is 75.9% higher than the AMD Radeon Pro 555X's 12628.

Q: Does the Radeon Pro 555X win any benchmark against the GTX 1660 SUPER?

A: No. The head-to-head data shows zero wins for the AMD card across Geekbench OpenCL and Geekbench Vulkan.

Q: How does the memory bandwidth compare?

A: The GTX 1660 SUPER has 336.0 GB/s bandwidth from its 6 GB GDDR6 memory on a 192-bit bus. The Radeon Pro 555X has 94.08 GB/s from 4 GB GDDR5 on a 128-bit bus.

Q: What is the power consumption difference?

A: The Radeon Pro 555X has a 75W TDP and requires no power connectors. The GTX 1660 SUPER has a 125W TDP and requires one 8-pin power connector, with a suggested 300W PSU.

Q: Which card has better API support?

A: The GTX 1660 SUPER supports DirectX 12 (12_1) and Vulkan 1.4, while the Radeon Pro 555X supports DirectX 12 (12_0) and Vulkan 1.3. Both support OpenGL 4.6.

Q: Are these cards still in production?

A: No, both are marked end-of-life. The Radeon Pro 555X was released on 2018-07-15, and the GTX 1660 SUPER on 2019-10-28.

Architecture Differences

The AMD Radeon Pro 555X uses the Polaris 21 chip based on GCN 4.0 architecture, manufactured on a 14 nm process at GlobalFoundries. It contains 3,000 million transistors on a 123 mm² die, resulting in a transistor density of 24.4M per mm². This is a mature, power-efficient design from 2018, built specifically for Apple's Mac lineup. The GCN 4.0 architecture supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.3. Its FP16 performance matches its FP32 at 1,393.2 GFLOPS, indicating a 1:1 ratio.

The NVIDIA GeForce GTX 1660 SUPER uses the TU116 chip based on Turing architecture, manufactured on a 12 nm process at TSMC. It packs 6,600 million transistors on a 284 mm² die, giving a transistor density of 23.2M per mm². Despite the smaller process node, the density is slightly lower than the AMD chip due to the larger, more complex design. The Turing architecture supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. Its FP16 performance is 10.05 TFLOPS, which is double its FP32 of 5.027 TFLOPS, indicating a 2:1 ratio. This is a key architectural difference: the NVIDIA card can accelerate FP16 workloads, while the AMD card's FP16 and FP32 are identical.

Neither card has dedicated ray tracing cores or tensor cores, so both rely on traditional shader-based rendering. The GTX 1660 SUPER is part of the GeForce 16 series, which omits RT and Tensor cores found in the RTX 20 series. The Radeon Pro 555X is part of the Radeon Pro Mac (500X Series) generation, a workstation-oriented lineup. The architecture differences explain the benchmark gaps: the Turing chip has nearly double the shading units (1408 vs 768), more than double the TMUs (88 vs 48), and triple the ROPs (48 vs 16).

Specification Differences

The two cards differ in nearly every measurable specification. The Radeon Pro 555X has 4 GB of GDDR5 memory, while the GTX 1660 SUPER has 6 GB of GDDR6. Memory bus width is 128-bit versus 192-bit, and bandwidth is 94.08 GB/s versus 336.0 GB/s. The NVIDIA card's memory clock is 1750 MHz (14 Gbps effective), while the AMD card's is 1470 MHz (5.9 Gbps effective). The GTX 1660 SUPER has a base clock of 1530 MHz and a boost clock of 1785 MHz, while the Radeon Pro 555X lists no base or boost clocks in the data.

Compute units differ significantly: the Radeon Pro 555X has 768 shading units, 48 TMUs, and 16 ROPs. The GTX 1660 SUPER has 1408 shading units, 88 TMUs, and 48 ROPs. Pixel rate is 14.51 GPixel/s versus 85.68 GPixel/s, and texture rate is 43.54 GTexel/s versus 157.1 GTexel/s. FP32 performance is 1,393.2 GFLOPS versus 5.027 TFLOPS. The GTX 1660 SUPER's launch MSRP was 229 USD. The Radeon Pro 555X has no launch MSRP listed.

Physical specifications also contrast sharply. The Radeon Pro 555X is an IGP with no power connectors and a 75W TDP. The GTX 1660 SUPER is a dual-slot card measuring 229 mm in length, 111 mm in height, and 35 mm in width, requiring a 1x 8-pin power connector and a 300W suggested PSU. The bus interface is PCIe 3.0 x8 for the AMD card and PCIe 3.0 x16 for the NVIDIA card. Display outputs are portable-device-dependent for the Radeon, while the GTX 1660 SUPER offers 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a. The Radeon Pro 555X's predecessor and successor are both listed as null, while the GTX 1660 SUPER's predecessor is GeForce 10 and successor is GeForce 20.