AMD Radeon RX 6600S vs NVIDIA GeForce GTX 1650 SUPER Comparison

The NVIDIA GeForce GTX 1650 SUPER and the AMD Radeon RX 6600S are two end-of-life graphics solutions from different eras, with the former being a desktop Turing card and the latter a mobile RDNA 2 part. The benchmark data reveals a clear performance hierarchy, with the AMD Radeon RX 6600S dominating the majority of tests, while the NVIDIA card secures a single, notable victory in 2D workloads.

Where Each One Wins

The data splits these two GPUs along clear functional lines. The AMD Radeon RX 6600S is the decisive winner in nearly every 3D and compute scenario, taking 7 out of 8 head-to-head benchmarks. Its biggest margins come in legacy DirectX 10 and modern DirectX 11 workloads, where it leads by 38.3% and 30.5%, respectively. This pattern suggests the RX 6600S is not just faster in raw throughput but also more efficient at translating that throughput into frame rate in both older and newer API environments.

The NVIDIA GeForce GTX 1650 SUPER’s sole victory is in the Passmark G2D test, scoring 749 against the AMD’s 647, a 15.8% advantage. This indicates that for pure 2D desktop composition, window management, and basic office productivity, the GTX 1650 SUPER holds a distinct edge. However, this is a narrow win; in the more demanding Passmark G3D test, which measures overall 3D graphics performance, the RX 6600S pulls ahead by 19.5%, scoring 12649 versus 10179. The AMD card also leads in compute-heavy tasks like Geekbench OpenCL (66435 vs 43875, a 34% lead) and Passmark GPU Compute (4879 vs 4477, an 8.2% lead), making it the clear choice for any workload that leverages general-purpose GPU processing.

Architecture Differences

The two cards represent fundamentally different design philosophies and generations. The GTX 1650 SUPER is built on NVIDIA’s Turing architecture, manufactured on a 12 nm process at TSMC. It uses the TU116 chip, which contains 6,600 million transistors on a 284 mm² die, yielding a transistor density of 23.2M / mm². In contrast, the RX 6600S is based on AMD’s RDNA 2.0 architecture, fabricated on a more advanced 7 nm process, also at TSMC. Its Navi 23 chip packs 11,060 million transistors into a smaller 237 mm² die, achieving a much higher density of 46.7M / mm². This process advantage is a key factor in the AMD card’s higher performance and lower power draw.

The compute configurations differ substantially. The RX 6600S features 1792 shading units, 112 texture mapping units (TMUs), and 64 raster operations pipelines (ROPs). The GTX 1650 SUPER is configured with fewer resources: 1280 shading units, 80 TMUs, and 32 ROPs. This difference in raw hardware resources is reflected in the fill rates, with the AMD card delivering a pixel rate of 128.0 GPixel/s and a texture rate of 224.0 GTexel/s, versus the NVIDIA card’s 55.20 GPixel/s and 138.0 GTexel/s. Furthermore, the RX 6600S includes 28 dedicated ray tracing cores, a feature entirely absent from the GTX 1650 SUPER, allowing it to support DirectX 12 Ultimate (12_2) APIs.

Memory subsystems are similar in capacity but differ in speed. Both cards have 4 GB of GDDR6 memory on a 128-bit bus, but the RX 6600S operates its memory at 1750 MHz (14 Gbps effective), yielding a bandwidth of 224.0 GB/s. The GTX 1650 SUPER’s memory runs at 1500 MHz (12 Gbps effective), providing 192.0 GB/s. The AMD card also has a faster memory clock and a higher boost clock of 2000 MHz compared to the NVIDIA’s 1725 MHz, contributing to its higher FP32 throughput of 7.168 TFLOPS versus 4.416 TFLOPS.

The Verdict

From the data, the choice is straightforward for most users. The AMD Radeon RX 6600S is the superior performer in the vast majority of tasks, offering a 19.5% lead in Passmark G3D and a 34% lead in Geekbench OpenCL. Its advantages in DirectX 10, 11, and 12 benchmarks, along with its support for ray tracing and DirectX 12 Ultimate, make it the more future-proof and capable option for gaming and general compute. The GTX 1650 SUPER’s only significant advantage lies in 2D performance, where its 15.8% lead in the G2D test suggests it may be snappier for desktop use.

However, the context of the cards matters. The RX 6600S is a mobile part with an IGP form factor and no power connectors, designed to be integrated into laptops. Its 80 W TDP is lower than the GTX 1650 SUPER’s 100 W, and it requires no external power, making it more suitable for portable systems. The GTX 1650 SUPER, a dual-slot desktop card with a 6-pin connector, is a legacy component now at end-of-life. Therefore, for a new purchase in a laptop, the RX 6600S is the clear winner. For a desktop build where 2D performance is the primary concern, the GTX 1650 SUPER holds a niche advantage, but its overall 3D performance is significantly behind.

FAQ

Q: Which GPU has better overall 3D performance?

A: The AMD Radeon RX 6600S is significantly faster, scoring 12649 in Passmark G3D compared to the NVIDIA GeForce GTX 1650 SUPER’s 10179, a 19.5% difference.

Q: Does the NVIDIA card win any benchmark?

A: Yes, the NVIDIA GeForce GTX 1650 SUPER wins the Passmark G2D test with a score of 749, which is 15.8% higher than the AMD Radeon RX 6600S’s score of 647.

Q: Are these two cards similar in memory configuration?

A: Both cards feature 4 GB of GDDR6 memory on a 128-bit bus. However, the AMD Radeon RX 6600S has a higher memory bandwidth of 224.0 GB/s compared to the NVIDIA’s 192.0 GB/s.

Q: What is the difference in their compute capabilities?

A: The AMD Radeon RX 6600S offers significantly higher compute performance, leading by 34% in Geekbench OpenCL (66435 vs 43875) and by 8.2% in Passmark GPU Compute (4879 vs 4477).

Q: Which GPU is more power-efficient based on the data?

A: The AMD Radeon RX 6600S has a lower TDP of 80 W and requires no power connectors, whereas the NVIDIA GeForce GTX 1650 SUPER has a 100 W TDP and needs a 6-pin connector.

Q: Does the AMD card support newer graphics features?

A: Yes, the AMD Radeon RX 6600S supports DirectX 12 Ultimate (12_2) and includes 28 ray tracing cores, while the NVIDIA GeForce GTX 1650 SUPER supports DirectX 12 (12_1) and has no ray tracing cores.

Head-to-Head Benchmarks

The most decisive victory for the AMD Radeon RX 6600S is in the Geekbench OpenCL test, where it scores 66435 against the GTX 1650 SUPER’s 43875, a 34% margin. This is a massive gap that highlights the AMD card’s superior raw compute throughput. In DirectX 10, the AMD card wins with a score of 81 versus 50, a 38.3% lead, showing that even older APIs scale well with its hardware. DirectX 11 results follow the same trend, with the RX 6600S scoring 105 to the NVIDIA’s 73, a 30.5% advantage. Even in DirectX 12, where the NVIDIA Turing architecture is generally considered strong, the AMD card maintains a 19.6% lead (56 vs 45).

The AMD card also secures a 15.9% win in DirectX 9 (176 vs 148), indicating a broad compatibility advantage across all API generations. In the Passmark G3D test, the RX 6600S’s 12649 score beats the GTX 1650 SUPER’s 10179 by 19.5%, which is a representative measure of overall 3D gaming performance. The compute-focused Passmark GPU Compute test also goes to AMD, with a score of 4879 versus 4477, an 8.2% lead. The single counter-example is the Passmark G2D test, where the NVIDIA card’s 749 score is 15.8% higher than the AMD’s 647, suggesting that the GTX 1650 SUPER has a faster 2D engine for desktop rendering tasks.