AMD Radeon RX 6600S vs NVIDIA GeForce GTX 590 Comparison

Head-to-Head Benchmarks

The recorded database contains only one direct head-to-head benchmark between the NVIDIA GeForce GTX 590 and the AMD Radeon RX 6600S: Geekbench OpenCL. In that test, the AMD Radeon RX 6600S scores 66,435, while the NVIDIA GeForce GTX 590 scores 12,830. That is a delta of -80.7% from the AMD card's perspective, meaning the GTX 590 trails by roughly five-fold in raw compute throughput. The RX 6600S wins the sole head-to-head comparison, giving it a clean 1-0 record in wins.

Looking at the broader database context, the GTX 590's OpenCL score of 12,830 places it at the 52nd percentile among all GPUs. Its nearest rivals in the database include the AMD Radeon Pro 455 at 12,831 (a 0% delta), the AMD FirePro W5100 at 12,847 (-0.1%), the AMD Radeon 740M at 12,870 (-0.3%), and the NVIDIA GeForce GTX 670 at 12,773 (+0.4%). The GTX 590 essentially sits in a tight cluster; it is statistically indistinguishable from these cards, with all deltas within a fraction of a percent. This suggests that despite its age, its OpenCL performance lands in a familiar mid-range bracket.

The RX 6600S, with its Geekbench OpenCL score of 66,435, sits at the 49th percentile among all GPUs. Its nearest rivals include the AMD Radeon R9 M275X at 10,582 (+0.4% delta relative to the RX 6600S), the NVIDIA GeForce GTX 560 Ti at 10,690 (-0.6%), the NVIDIA Quadro K2200 at 10,761 (-1.2%), and the AMD Radeon RX 550X at 10,481 (+1.4%). These deltas are also small, but the absolute scores are dramatically lower than the RX 6600S's own result. The database average benchmark score for the RX 6600S, however, is 10,629, which pulls its percentile down because it includes multiple Passmark tests where the card scores far lower than its OpenCL peak.

The gap in the head-to-head is stark: the RX 6600S delivers 53,605 more points in OpenCL. That is not a marginal improvement; it is a generational leap. The GTX 590's Fermi architecture, despite having 512 shading units and a 384-bit memory bus, cannot match the RDNA 2.0 architecture's compute efficiency. The data shows a single decisive benchmark, and the winner is unambiguous.

Where Each One Wins

Based on the recorded benchmarks, the AMD Radeon RX 6600S wins the only direct comparison, so it takes the compute crown. The Geekbench OpenCL result reflects general-purpose GPU compute, which is often used in rendering, physics simulations, and certain productivity workloads. The RX 6600S's 66,435 score indicates strong raw floating-point throughput, consistent with its 7.168 TFLOPS FP32 rating and 14.34 TFLOPS FP16 capability. The GTX 590's 1,244.2 GFLOPS FP32 is far lower, and its older Fermi architecture lacks the parallel efficiency of RDNA 2.0.

However, the GTX 590 has its own strengths in the database, even if they do not show up in head-to-head wins. Its pixel rate is 19.46 GPixel/s and texture rate is 38.91 GTexel/s, which are modest but functional figures. It also has 48 ROPs and 64 TMUs, which historically supported high-resolution rasterization. The RX 6600S, by contrast, offers 128.0 GPixel/s and 224.0 GTexel/s, with 64 ROPs and 112 TMUs. Those numbers are not directly compared in a benchmark, but they suggest the RX 6600S would dominate in fill-rate-bound scenarios.

For gaming-specific workloads, the RX 6600S supports DirectX 12 Ultimate (12_2), Vulkan 1.4, and has 28 ray tracing cores. The GTX 590 only reaches DirectX 12 (11_0) and lacks Vulkan support entirely. The RX 6600S also has a 4 GB GDDR6 memory pool on a 128-bit bus with 224.0 GB/s bandwidth, while the GTX 590 uses 1536 MB GDDR5 on a 384-bit bus with 164.0 GB/s bandwidth. The RX 6600S's higher bandwidth and larger capacity give it an edge in modern game assets.

The GTX 590's advantage lies in its PCIe 2.0 x16 interface, which is more universally compatible with older motherboards, but that is not a performance win. Its dual-slot cooler and 2x 8-pin power connectors are also not performance metrics. In terms of raw wins, the RX 6600S takes the only recorded benchmark, so it is the clear victor in any use case that relies on OpenCL compute. For legacy DirectX 9 or 10 workloads, the GTX 590 might hold its own, but the RX 6600S's Passmark DirectX 9 score of 176 and DirectX 10 score of 81 indicate it handles those APIs too, albeit with lower absolute numbers than its OpenCL result. The database does not record a DirectX 9 or 10 score for the GTX 590, so no direct comparison is possible.

The Verdict

The data points to one conclusion: the AMD Radeon RX 6600S is the superior card in the recorded head-to-head. The Geekbench OpenCL score of 66,435 versus 12,830 is a decisive margin, and the RX 6600S also has architectural advantages in memory bandwidth, shading units, and API support. The GTX 590's only solace is its 52nd percentile ranking, which is slightly higher than the RX 6600S's 49th percentile, but that ranking is based on different benchmark suites and does not reflect the direct comparison.

A user who prioritizes modern compute performance, ray tracing, or DirectX 12 Ultimate should choose the RX 6600S. Its 7 nm process node, 11,060 million transistors, and 28 ray tracing cores make it a far more capable card for contemporary workloads. The GTX 590, with its 40 nm node and 3,000 million transistors, is a relic of the Fermi era, and its 365 W TDP versus the RX 6600S's 80 W TDP shows a massive efficiency gap. The RX 6600S also requires no external power connectors, while the GTX 590 needs 2x 8-pin and a 750 W suggested PSU.

For legacy system builders, the GTX 590 might fit a vintage build, but the benchmark data offers no reason to pick it over the RX 6600S. The RX 6600S wins the only test, and its other recorded scores (Passmark G3D at 12,649, Passmark GPU Compute at 4,879) indicate balanced performance across multiple APIs. The GTX 590 has no other recorded benchmarks, so its overall capability is less documented. The verdict is straightforward: the RX 6600S is the better performer in the database's measurements.

FAQ

Q: What is the score difference in the head-to-head Geekbench OpenCL test?

A: The AMD Radeon RX 6600S scores 66,435, while the NVIDIA GeForce GTX 590 scores 12,830, a delta of -80.7% from the RX 6600S's perspective.

Q: Which card has a higher memory bandwidth?

A: The AMD Radeon RX 6600S has 224.0 GB/s bandwidth, compared to 164.0 GB/s for the NVIDIA GeForce GTX 590.

Q: Does the GTX 590 support Vulkan?

A: No, the database lists no Vulkan support for the GTX 590, while the RX 6600S supports Vulkan 1.4.

Q: What is the TDP difference between the two cards?

A: The GTX 590 has a TDP of 365 W, while the RX 6600S has a TDP of 80 W.

Q: Which card has more shading units?

A: The RX 6600S has 1,792 shading units, compared to 512 for the GTX 590.

Q: What is the percentile ranking for each card?

A: The GTX 590 sits at the 52nd percentile among all GPUs, while the RX 6600S sits at the 49th percentile.

Architecture Differences

The two cards come from entirely different eras and design philosophies. The NVIDIA GeForce GTX 590 uses the GF110 chip built on a 40 nm process at TSMC, with 3,000 million transistors on a 520 mm² die. Its transistor density is 5.8 million per mm². The architecture is Fermi 2.0, part of the GeForce 500 generation, released on March 23, 2011. It has 512 shading units, 64 TMUs, and 48 ROPs. Memory is 1536 MB of GDDR5 on a 384-bit bus, running at 854 MHz (3.4 Gbps effective). The card's FP32 compute is 1,244.2 GFLOPS, and it lacks any ray tracing or tensor cores. It supports DirectX 12 (11_0) and OpenGL 4.6, but no Vulkan. It connects via PCIe 2.0 x16.

The AMD Radeon RX 6600S uses the Navi 23 chip on a 7 nm process at TSMC, with 11,060 million transistors on a 237 mm² die. Its transistor density is 46.7 million per mm², a massive jump from the GTX 590. The architecture is RDNA 2.0, part of the Radeon RX 6000 series (Navi Mobile generation), released on January 3, 2022. It has 1,792 shading units, 112 TMUs, and 64 ROPs, plus 28 ray tracing cores. Memory is 4 GB of GDDR6 on a 128-bit bus, running at 1750 MHz (14 Gbps effective). FP32 compute is 7.168 TFLOPS, and FP16 is 14.34 TFLOPS with a 2:1 ratio. It supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. It connects via PCIe 4.0 x8 and is an integrated graphics package (IGP) with no external power connectors.

The process node difference is stark: 40 nm versus 7 nm, which explains the transistor density gap. The RX 6600S packs nearly four times the transistors into less than half the die area. Clock speeds also differ: the RX 6600S has a base clock of 1700 MHz, a game clock of 1881 MHz, and a boost clock of 2000 MHz, while the GTX 590 has no base or boost clocks recorded in the database. The RX 6600S's pixel rate (128.0 GPixel/s) and texture rate (224.0 GTexel/s) dwarf the GTX 590's 19.46 GPixel/s and 38.91 GTexel/s. Power draw is another major divider: 80 W versus 365 W, with the RX 6600S requiring no external power and the GTX 590 needing 2x 8-pin connectors. The GTX 590 is dual-slot and 279 mm long, while the RX 6600S has no recorded dimensions and is an IGP. Display outputs also differ: the GTX 590 offers 3x DVI and 1x mini-DisplayPort, while the RX 6600S is portable-device dependent. The GTX 590's launch MSRP was 699 USD, while the RX 6600S has no recorded launch MSRP.