NVIDIA GeForce GTX 560 Ti vs NVIDIA GeForce GTX 590 Comparison

The Verdict

The NVIDIA GeForce GTX 590 is the clear performance leader in this comparison, posting a Geekbench OpenCL score of 12,830 against 10,690 for the GTX 560 Ti, a 20% advantage. The GTX 590 also sits in the 52nd percentile of all GPUs in the database, while the GTX 560 Ti lands at the 49th percentile. For tasks that scale with raw compute throughput, the GTX 590 is the stronger choice, and the data shows it outperforms the GTX 670, a notable rival, by 0.4% in average score.

The GTX 560 Ti, however, is not without its own appeal. It delivers a texture rate of 52.67 GTexel/s, which is 35% higher than the GTX 590's 38.91 GTexel/s, making it the better option for workloads that are fill-rate bound. Its smaller footprint, lower power draw, and reduced power connector requirements also make it far easier to integrate into a typical desktop build. The GTX 560 Ti is the sensible pick for users with modest power delivery and limited chassis space, while the GTX 590 is for those who prioritize raw compute performance and have the infrastructure to support a 365 W flagship.

Architecture Differences

Both GPUs are built on NVIDIA's Fermi 2.0 architecture and use TSMC's 40 nm process node, so the foundational design philosophy is shared. The differences lie in the scale and configuration of the silicon. The GTX 590 uses the GF110 chip, which packs 3,000 million transistors onto a 520 mm² die, yielding a transistor density of 5.8M per mm². The GTX 560 Ti uses the GF114 chip, with 1,950 million transistors on a 332 mm² die, for a slightly higher density of 5.9M per mm².

The GTX 590's larger die houses significantly more execution resources. It features 512 shading units, 64 texture mapping units, and 48 raster output units. The GTX 560 Ti, by contrast, has 384 shading units, 64 texture mapping units, and 32 raster output units. The shading unit count is a 33% advantage for the GTX 590, while the TMU count is identical, which explains the GTX 560 Ti's higher texture rate relative to its compute throughput.

Memory architecture also differs substantially. The GTX 590 carries 1536 MB of GDDR5 on a 384-bit bus, delivering 164.0 GB/s of bandwidth. The GTX 560 Ti has 1024 MB of GDDR5 on a 256-bit bus, for 128.3 GB/s. The GTX 590's memory clock is rated at 854 MHz with 3.4 Gbps effective, while the GTX 560 Ti runs its memory at 1002 MHz with 4 Gbps effective. Despite the GTX 560 Ti's higher memory clock, the GTX 590's wider bus gives it a 28% bandwidth advantage.

Both cards support DirectX 12 (11_0) and OpenGL 4.6, and neither has Vulkan support listed in the database. Neither card includes ray tracing or tensor cores, which is consistent with their Fermi 2.0 generation. The GTX 590 has a dual-slot cooler and requires two 8-pin power connectors, while the GTX 560 Ti also uses a dual-slot cooler but only needs two 6-pin connectors.

Head-to-Head Benchmarks

The only recorded head-to-head benchmark in the database is Geekbench OpenCL, and the GTX 590 wins decisively. It scores 12,830 against the GTX 560 Ti's 10,690, a delta of 20%. This is a substantial margin that reflects the GTX 590's much larger shader array and wider memory bus. In raw compute terms, the GTX 590's FP32 throughput is listed at 1,244.2 GFLOPS, while the GTX 560 Ti is rated at 1,263.4 GFLOPS. Interestingly, the GTX 560 Ti has a slightly higher theoretical FP32 figure, yet the GTX 590 still wins the OpenCL benchmark by 20%, suggesting that memory bandwidth and driver efficiency play a significant role in real-world OpenCL performance.

The GTX 590's nearest rivals in the database include the AMD Radeon Pro 455, which scores 12,831 and is effectively tied with a delta of 0%, and the AMD FirePro W5100 at 12,847, which is 0.1% ahead. The GTX 590 also edges out the NVIDIA GeForce GTX 670, which scores 12,773, by 0.4%. The GTX 560 Ti, meanwhile, sits in a lower performance tier. Its closest rival is the NVIDIA Quadro K2200 at 10,761, which is 0.7% ahead, and the AMD Radeon Pro 450 at 10,804, which is 1.1% ahead. The GTX 560 Ti does beat the AMD Radeon RX 6600S by 0.6% and the AMD Radeon R9 M275X by 1%.

The texture rate comparison is the one area where the GTX 560 Ti clearly wins. It posts 52.67 GTexel/s versus 38.91 GTexel/s for the GTX 590, a 35% advantage. This is a direct result of both cards having 64 TMUs, but the GTX 560 Ti's higher clock speed allows it to push more texels per second. The pixel rate tells the opposite story: the GTX 590 achieves 19.46 GPixel/s, while the GTX 560 Ti manages 13.17 GPixel/s, a 48% advantage for the GTX 590, driven by its 48 ROPs versus 32.

Specification Differences

The two cards diverge on nearly every major specification except for architecture, process node, foundry, generation, and API support. The table below highlights only the fields where the two differ.

| Specification | NVIDIA GeForce GTX 590 | NVIDIA GeForce GTX 560 Ti |

| --- | --- | --- |

| Chip | GF110 | GF114 |

| Transistors | 3,000 million | 1,950 million |

| Die Size | 520 mm² | 332 mm² |

| Transistor Density | 5.8M / mm² | 5.9M / mm² |

| Memory Clock | 854 MHz, 3.4 Gbps effective | 1002 MHz, 4 Gbps effective |

| Memory Size | 1536 MB | 1024 MB |

| Memory Bus Width | 384 bit | 256 bit |

| Memory Bandwidth | 164.0 GB/s | 128.3 GB/s |

| Shading Units | 512 | 384 |

| ROPs | 48 | 32 |

| Pixel Rate | 19.46 GPixel/s | 13.17 GPixel/s |

| Texture Rate | 38.91 GTexel/s | 52.67 GTexel/s |

| FP32 | 1,244.2 GFLOPS | 1,263.4 GFLOPS |

| TDP | 365 W | 170 W |

| Power Connectors | 2x 8-pin | 2x 6-pin |

| Suggested PSU | 750 W | 450 W |

| Display Outputs | 3x DVI, 1x mini-DisplayPort | 2x DVI, 1x mini-HDMI 1.3a |

| Dimensions | 279 mm (11 inches) long, 111 mm (4.4 inches) high, 40 mm (1.6 inches) wide | 229 mm (9 inches) long |

| Release Date | 2011-03-23 | 2011-01-24 |

| Launch MSRP | 699 USD | 249 USD |

The GTX 590 is longer, taller, and wider, and it consumes more than twice the power of the GTX 560 Ti. The GTX 590's suggested PSU is 750 W, while the GTX 560 Ti only needs 450 W. The GTX 560 Ti's display outputs are limited to two DVI and one mini-HDMI 1.3a, whereas the GTX 590 offers three DVI and one mini-DisplayPort. The GTX 590 also has a later release date by roughly two months.

FAQ

Q: Which GPU is faster in Geekbench OpenCL?

A: The NVIDIA GeForce GTX 590 scores 12,830, which is 20% higher than the GTX 560 Ti's 10,690.

Q: Does the GTX 560 Ti have any performance advantage over the GTX 590?

A: Yes, the GTX 560 Ti has a texture rate of 52.67 GTexel/s, which is 35% higher than the GTX 590's 38.91 GTexel/s.

Q: How do the two cards compare in memory bandwidth?

A: The GTX 590 offers 164.0 GB/s over a 384-bit bus, while the GTX 560 Ti offers 128.3 GB/s over a 256-bit bus, a 28% advantage for the GTX 590.

Q: What is the power consumption difference?

A: The GTX 590 has a TDP of 365 W and requires a 750 W suggested PSU, while the GTX 560 Ti has a TDP of 170 W and needs only a 450 W suggested PSU.

Q: Are both cards based on the same architecture?

A: Yes, both use Fermi 2.0 architecture from the GeForce 500 generation, manufactured on TSMC's 40 nm process.

Q: How does the GTX 590 compare to other GPUs in the database?

A: The GTX 590 sits at the 52nd percentile of all GPUs, with nearest rivals including the AMD Radeon Pro 455 at 12,831 and the AMD FirePro W5100 at 12,847. The GTX 670 trails it by 0.4%.