AMD Radeon Pro 450 vs NVIDIA GeForce GTX 1660 SUPER Comparison

The Verdict

The NVIDIA GeForce GTX 1660 SUPER is the clear performance leader in this comparison. The database shows it wins both shared benchmark tests decisively, with an average benchmark score of 12986 compared to 10804 for the AMD Radeon Pro 450. The NVIDIA part sits at the 53rd percentile among all GPUs, while the AMD card sits at the 49th percentile, a meaningful gap in overall ranking.

The AMD Radeon Pro 450 is a low-power mobile workstation part, designed for portability rather than raw throughput. Its 35 W TDP, MXM module form factor, and lack of a suggested PSU rating make it suitable for compact or battery-powered systems. The GeForce GTX 1660 SUPER, by contrast, is a dual-slot desktop card with a 125 W TDP and a 300 W suggested PSU, clearly aimed at desktop gaming and general compute workloads.

Who should pick which? The data is unambiguous: if the workload requires sustained 3D rendering, OpenCL compute, or Vulkan performance, the GeForce GTX 1660 SUPER is the only rational choice. The AMD card is only defensible for systems with strict power or space constraints, and even then the performance penalty is severe. The GeForce GTX 1660 SUPER delivers 483.1% higher OpenCL scores and 442.9% higher Vulkan scores in direct head-to-head tests. For any workload measured in the database, the NVIDIA part is the stronger option.

Architecture Differences

The two GPUs come from different architectural generations and foundries. The NVIDIA GeForce GTX 1660 SUPER uses the TU116 chip built on a 12 nm process at TSMC, with 6,600 million transistors on a 284 mm² die. The AMD Radeon Pro 450 uses the Baffin chip built on a 14 nm process at GlobalFoundries, with 3,000 million transistors on a 123 mm² die. Despite the smaller absolute transistor count, the AMD chip has a slightly higher transistor density at 24.4M per mm² versus 23.2M per mm² for NVIDIA.

The architectural lineage differs completely. NVIDIA's TU116 is part of the Turing architecture, in the GeForce 16 generation, following the GeForce 10 series and preceding the GeForce 20 series. AMD's Baffin is based on GCN 4.0, from the Radeon Pro Mac (400 Series) generation. The NVIDIA card lists a predecessor (GeForce 10) and successor (GeForce 20), while the AMD card has neither listed in the database.

Compute resources differ by a wide margin. The GeForce GTX 1660 SUPER has 1,408 shading units, 88 texture mapping units, and 48 ROPs. The Radeon Pro 450 has 640 shading units, 40 TMUs, and 16 ROPs. The NVIDIA card's pixel rate is 85.68 GPixel/s versus 12.80 GPixel/s for AMD, and texture rate is 157.1 GTexel/s versus 32.00 GTexel/s. The FP32 throughput is 5.027 TFLOPS for NVIDIA versus 1,024.0 GFLOPS for AMD.

Memory architecture also diverges sharply. The GeForce GTX 1660 SUPER uses 6 GB of GDDR6 on a 192-bit bus, with 336.0 GB/s of bandwidth. The Radeon Pro 450 uses 2 GB of GDDR5 on a 128-bit bus, with 81.28 GB/s of bandwidth. Neither card has ray tracing cores or tensor cores listed in the database.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 1660 SUPER has an average benchmark score of 12986, while the AMD Radeon Pro 450 scores 10804. The NVIDIA card also holds the 53rd percentile among all GPUs versus the 49th percentile for AMD.

Q: How do the two cards compare in Vulkan performance?

A: In the geekbench_vulkan test, the NVIDIA GeForce GTX 1660 SUPER scores 57102 against 10518 for the AMD Radeon Pro 450, a 442.9% advantage for NVIDIA.

Q: What memory configurations do these cards use?

A: The GeForce GTX 1660 SUPER has 6 GB of GDDR6 on a 192-bit bus with 336.0 GB/s bandwidth. The Radeon Pro 450 has 2 GB of GDDR5 on a 128-bit bus with 81.28 GB/s bandwidth.

Q: Are these cards still in production?

A: Both are marked as end-of-life in the database. The NVIDIA card was released on 2019-10-28, and the AMD card was released on 2016-10-29.

Q: Which card supports newer API versions?

A: The NVIDIA GeForce GTX 1660 SUPER supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The AMD Radeon Pro 450 supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.3.

Q: What are the power requirements for each card?

A: The GeForce GTX 1660 SUPER has a 125 W TDP and a 300 W suggested PSU, requiring a single 8-pin power connector. The Radeon Pro 450 has a 35 W TDP, with no power connector or suggested PSU listed in the database.

Specification Differences

The following fields differ between the two GPUs in the recorded data:

• Chip: TU116 versus Baffin
• Architecture: Turing versus GCN 4.0
• Generation: GeForce 16 versus Radeon Pro Mac (400 Series)
• Process node: 12 nm versus 14 nm
• Foundry: TSMC versus GlobalFoundries
• Transistors: 6,600 million versus 3,000 million
• Die size: 284 mm² versus 123 mm²
• Transistor density: 23.2M / mm² versus 24.4M / mm²
• Memory size: 6 GB versus 2 GB
• Memory type: GDDR6 versus GDDR5
• Memory bus: 192 bit versus 128 bit
• Memory bandwidth: 336.0 GB/s versus 81.28 GB/s
• Memory clock: 1750 MHz (14 Gbps effective) versus 1270 MHz (5.1 Gbps effective)
• Base clock: 1530 MHz versus not listed
• Boost clock: 1785 MHz versus not listed
• Shading units: 1408 versus 640
• TMUs: 88 versus 40
• ROPs: 48 versus 16
• Pixel rate: 85.68 GPixel/s versus 12.80 GPixel/s
• Texture rate: 157.1 GTexel/s versus 32.00 GTexel/s
• FP32: 5.027 TFLOPS versus 1,024.0 GFLOPS
• FP16: 10.05 TFLOPS (2:1) versus 1,024.0 GFLOPS (1:1)
• TDP: 125 W versus 35 W
• Slot width: Dual-slot versus MXM Module
• Power connectors: 1x 8-pin versus not listed
• Suggested PSU: 300 W versus not listed
• Bus interface: PCIe 3.0 x16 versus PCIe 3.0 x8
• Display outputs: 1x DVI, 1x HDMI 2.0, 1x DisplayPort 1.4a versus Portable Device Dependent
• DirectX support: 12 (12_1) versus 12 (12_0)
• Vulkan support: 1.4 versus 1.3
• Dimensions: 229 mm x 111 mm x 35 mm versus not listed
• Release date: 2019-10-28 versus 2016-10-29
• Launch MSRP: 229 USD versus not listed

Head-to-Head Benchmarks

The database contains two direct comparisons between these GPUs, and both are overwhelming NVIDIA victories.

In the geekbench_opencl test, the NVIDIA GeForce GTX 1660 SUPER scores 52490 against 9002 for the AMD Radeon Pro 450. This is a 483.1% delta in favor of NVIDIA. OpenCL compute is a common workload for GPU acceleration in rendering, video processing, and scientific applications, so this gap has broad practical implications. The AMD card's score of 9002 is only about 17% of the NVIDIA result, indicating a fundamental compute throughput disparity that aligns with the FP32 and memory bandwidth differences.

In the geekbench_vulkan test, the NVIDIA card scores 57102 versus 10518 for AMD, a 442.9% advantage. Vulkan is a modern low-level graphics API, and the NVIDIA card's support for Vulkan 1.4 versus AMD's Vulkan 1.3 adds a feature-level advantage on top of the raw performance gap.

The NVIDIA card also holds a significant advantage in the broader benchmark suite available in the database. While the AMD card only has three recorded benchmarks (geekbench_metal at 12893, geekbench_opencl at 9002, and geekbench_vulkan at 10518), the NVIDIA card has ten recorded benchmarks spanning DirectX 9 through DirectX 12, compute, and 2D tests. The NVIDIA card's passmark_g3d score is 12699, its passmark_gpu_compute score is 5076, and its geekbench_opencl score of 52490 is its best recorded OpenCL result.

The nearest rivals in the database also frame the comparison. The GeForce GTX 1660 SUPER sits between the NVIDIA Tesla M2090 (13075, 0.7% higher) and the NVIDIA GeForce RTX 3050 Ti Mobile (12940, 0.4% lower), placing it in a competitive mid-range performance band. The Radeon Pro 450 sits between the NVIDIA GeForce MX350 (10883, 0.7% higher) and the NVIDIA Quadro K2200 (10761, 0.4% lower), a much lower performance tier.

Where Each One Wins

The NVIDIA GeForce GTX 1660 SUPER wins in every measurable category in the database. It has higher raw compute throughput, more memory capacity, faster memory bandwidth, more shading units, more texture units, and more ROPs. It wins both head-to-head benchmark tests by margins of 483.1% and 442.9%. Its average benchmark score of 12986 puts it 20.2% ahead of the AMD card's 10804 average.

The AMD Radeon Pro 450 does have some advantages, though they are not performance-related. Its 35 W TDP makes it suitable for systems where power consumption is a constraint. Its MXM module form factor and portable-device-dependent display outputs suggest it is designed for laptops or compact workstations. Its transistor density of 24.4M / mm² is slightly higher than NVIDIA's 23.2M / mm², indicating a more compact design relative to its transistor count. Its release date of 2016-10-29 makes it an earlier product, and its lack of a listed launch MSRP suggests it was an OEM or mobile part rather than a retail desktop card.

The GeForce GTX 1660 SUPER is the choice for desktop users who need strong DirectX performance across multiple versions, OpenCL compute, or Vulkan rendering. Its recorded passmark scores across DirectX 9 (189), DirectX 10 (65), DirectX 11 (104), and DirectX 12 (50) show broad API coverage. Its 6 GB GDDR6 memory with 336.0 GB/s bandwidth supports larger textures and higher resolutions than the 2 GB GDDR5 configuration on the AMD card.

The Radeon Pro 450 is only defensible in scenarios where the 125 W TDP and dual-slot footprint of the NVIDIA card are unacceptable. In those constrained environments, the AMD card offers a functional but dramatically slower alternative. The data shows no benchmark category in which the AMD card outperforms the NVIDIA card, so the decision ultimately rests on system constraints rather than performance preferences.