AMD Radeon RX 7600M XT vs NVIDIA GeForce GTX 1660 SUPER Comparison

FAQ

Q: Which GPU wins the most head-to-head benchmark comparisons?

A: The AMD Radeon RX 7600M XT wins 8 of the 10 shared benchmarks, while the NVIDIA GeForce GTX 1660 SUPER wins only 2. The AMD card's victories include 3DMark Steel Nomad DX12, Geekbench OpenCL, Passmark DirectX 10, 11, 12, G2D, G3D, and GPU Compute.

Q: What is the largest performance gap between the two cards in any single test?

A: The largest gap is in Geekbench Vulkan, where the NVIDIA GeForce GTX 1660 SUPER scores 57102 versus the AMD's 27793, a 105.5% advantage for NVIDIA. Conversely, the AMD card leads by 37.6% in 3DMark Steel Nomad DX12 (2048 vs 1278).

Q: How do the two cards compare in overall average benchmark score?

A: The NVIDIA GeForce GTX 1660 SUPER has a higher average benchmark score of 12986, compared to the AMD Radeon RX 7600M XT's 12710. Despite this, the AMD card wins more individual head-to-head tests.

Q: Which card has better DirectX 9 legacy performance?

A: The NVIDIA GeForce GTX 1660 SUPER leads in Passmark DirectX 9 with a score of 189 versus 175 for the AMD, an 8% advantage. This is one of only two tests NVIDIA wins.

Q: What is the percentile ranking for each GPU among all GPUs?

A: The NVIDIA GeForce GTX 1660 SUPER sits at the 53rd percentile, while the AMD Radeon RX 7600M XT is at the 52nd percentile. Both cards are nearly identical in overall standing despite their architectural differences.

Q: Which card performs better in compute workloads?

A: The AMD Radeon RX 7600M XT wins Passmark GPU Compute with 7140 versus 5076 for NVIDIA, a 28.9% advantage. It also leads Geekbench OpenCL by 29.9% (74869 vs 52490).

Architecture Differences

The NVIDIA GeForce GTX 1660 SUPER is built on the Turing architecture using the TU116 chip, manufactured on a 12 nm process at TSMC. It packs 6,600 million transistors into a 284 mm² die, yielding a transistor density of 23.2 million per mm². The AMD Radeon RX 7600M XT uses the RDNA 3.0 architecture with the Navi 33 chip (codename "Hotpink Bonefish"), built on a 6 nm process also at TSMC. It contains 13,300 million transistors on a smaller 204 mm² die, achieving 65.2 million transistors per mm² — nearly three times the density of the NVIDIA chip.

The NVIDIA card features 1408 shading units, 88 texture mapping units, and 48 raster operation units. The AMD card counters with 2048 shading units, 128 TMUs, and 64 ROPs. Notably, the AMD GPU includes 32 ray tracing cores, while the NVIDIA card has none listed. Neither card has tensor cores.

Memory configurations differ substantially. The GTX 1660 SUPER uses 6 GB of GDDR6 on a 192-bit bus, providing 336.0 GB/s of bandwidth. The RX 7600M XT has 8 GB of GDDR6 on a narrower 128-bit bus, resulting in 288.0 GB/s of bandwidth — lower despite the larger capacity.

Clock behavior also diverges. NVIDIA lists a 1530 MHz base and 1785 MHz boost, while AMD shows a 1280 MHz base, 2023 MHz game clock, and 2469 MHz boost. The AMD's boost clock is substantially higher, contributing to its raw throughput advantages.

Process node differences are significant. The 12 nm NVIDIA process contrasts with the 6 nm AMD process, explaining the transistor density gap. This architectural generational leap is reflected in the AMD's higher FP32 compute of 20.23 TFLOPS versus NVIDIA's 5.027 TFLOPS.

Head-to-Head Benchmarks

The 3DMark Steel Nomad DX12 test shows a decisive AMD victory: 2048 versus 1278, a 37.6% margin. This is the largest single-test win for the AMD card and indicates stronger modern DX12 rasterization performance.

Geekbench OpenCL also favors AMD heavily, with 74869 versus 52490, a 29.9% advantage. This aligns with the AMD card's higher compute throughput and suggests better general-purpose GPU compute capability.

The most striking reversal comes in Geekbench Vulkan. The NVIDIA card scores 57102 against AMD's 27793, giving NVIDIA a 105.5% advantage — more than double the AMD score. This is the single largest delta in either direction across all tests.

Passmark tests paint a mixed picture. In DirectX 10, AMD leads 76 to 65 (14.5% ahead). In DirectX 11, AMD leads 137 to 104 (24.1% ahead). In DirectX 12, AMD leads 58 to 50 (13.8% ahead). However, in DirectX 9, NVIDIA wins 189 to 175 (8% ahead).

The 2D performance test (Passmark G2D) shows AMD ahead at 894 versus 805, a 10% margin. The 3D test (Passmark G3D) shows AMD leading 13907 to 12699, an 8.7% advantage. Finally, Passmark GPU Compute has AMD winning 7140 to 5076, a 28.9% margin.

Overall, AMD wins the modern API tests (DX10, DX11, DX12, OpenCL, Steel Nomad) and compute workloads. NVIDIA wins the Vulkan test decisively and edges out a narrow DirectX 9 victory.

Specification Differences

The two GPUs differ in nearly every major specification category. The NVIDIA card uses the TU116 chip on a 12 nm process, while AMD uses Navi 33 on 6 nm. Transistor counts are 6,600 million versus 13,300 million, and die sizes are 284 mm² versus 204 mm². Transistor density is 23.2M/mm² for NVIDIA and 65.2M/mm² for AMD.

Clock speeds differ: NVIDIA base is 1530 MHz and boost is 1785 MHz, while AMD base is 1280 MHz, game clock is 2023 MHz, and boost is 2469 MHz. Memory speed shows 1750 MHz (14 Gbps effective) for NVIDIA versus 2250 MHz (18 Gbps effective) for AMD.

Memory capacity and bus width differ: 6 GB on 192-bit for NVIDIA versus 8 GB on 128-bit for AMD. Bandwidth is 336.0 GB/s versus 288.0 GB/s. Shading units are 1408 versus 2048, TMUs are 88 versus 128, and ROPs are 48 versus 64. The AMD card has 32 ray tracing cores; NVIDIA has none.

Pixel rate is 85.68 GPixel/s for NVIDIA versus 158.0 GPixel/s for AMD. Texture rate is 157.1 GTexel/s versus 316.0 GTexel/s. FP32 is 5.027 TFLOPS versus 20.23 TFLOPS, and FP16 is 10.05 TFLOPS versus 40.45 TFLOPS.

TDP is 125 W for NVIDIA versus 120 W for AMD. Slot width is dual-slot for NVIDIA versus IGP for AMD. Power connectors are 1x 8-pin for NVIDIA versus none for AMD. The NVIDIA card uses PCIe 3.0 x16, while AMD uses PCIe 4.0 x16. Display outputs are 1x DVI, 1x HDMI 2.0, 1x DisplayPort 1.4a for NVIDIA versus "Portable Device Dependent" for AMD.

DirectX support differs: 12 (12_1) for NVIDIA versus 12 Ultimate (12_2) for AMD. Production status is end-of-life for NVIDIA versus active for AMD. Release dates are October 2019 versus January 2023.

The Verdict

The data presents a nuanced picture. The AMD Radeon RX 7600M XT wins the majority of head-to-head tests (8 of 10), including all modern API benchmarks and compute workloads. Its advantages in DirectX 10, 11, and 12 are consistent, ranging from 13.8% to 24.1%. The 3DMark Steel Nomad DX12 result shows a 37.6% lead, indicating substantially stronger current-generation rasterization performance.

However, the NVIDIA GeForce GTX 1660 SUPER is not without merit. Its Geekbench Vulkan score is 105.5% higher, a dramatic reversal that suggests driver or architectural strengths in that specific API. It also wins DirectX 9 by 8%, making it the better choice for legacy titles using that API. Additionally, its average benchmark score (12986) is slightly higher than AMD's (12710), and its percentile ranking (53rd) marginally exceeds AMD's (52nd).

For users prioritizing modern DirectX 12 workloads, compute tasks, or ray tracing capability, the AMD card is the clear choice based on benchmark data. For those running Vulkan-based applications or older DirectX 9 titles, the NVIDIA card holds a distinct advantage. The AMD card's higher FP32 throughput (20.23 TFLOPS) and larger memory pool (8 GB) suggest better future-proofing, while the NVIDIA card's higher bandwidth (336.0 GB/s) on a wider bus may benefit certain bandwidth-sensitive workloads.

Where Each One Wins

AMD Radeon RX 7600M XT wins in: DirectX 12 modern gaming (37.6% in Steel Nomad), OpenCL compute (29.9% ahead), DirectX 11 (24.1% ahead), DirectX 10 (14.5% ahead), DirectX 12 Passmark (13.8% ahead), 2D workloads (10% ahead), 3D rendering (8.7% ahead), and GPU compute (28.9% ahead). The 32 ray tracing cores provide hardware RT support absent from the NVIDIA card.

NVIDIA GeForce GTX 1660 SUPER wins in: Vulkan API performance (105.5% ahead in Geekbench Vulkan) and DirectX 9 legacy titles (8% ahead). Its higher memory bandwidth of 336.0 GB/s versus 288.0 GB/s may benefit specific bandwidth-bound scenarios, and its slightly higher average benchmark score (12986 versus 12710) reflects overall consistency.

The AMD card is the superior modern performer across most workloads, while the NVIDIA card retains specific API advantages that could matter for particular applications or older games.