AMD Radeon HD 7790 vs NVIDIA GeForce GTX 660 Ti Comparison

Head-to-Head Benchmarks

The database records only one benchmark score for the AMD Radeon HD 7790: a Geekbench Metal result of 17,666. The NVIDIA GeForce GTX 660 Ti, by contrast, has two recorded scores: a Geekbench OpenCL result of 15,113 and a Geekbench Vulkan result of 15,012. Because the two cards share no common benchmark test, a direct head-to-head comparison is not possible from the recorded data. The HD 7790's single score cannot be compared against either of the GTX 660 Ti's scores, as they run different APIs and measure different workloads.

What the data does show is how each card ranks among all GPUs. The HD 7790 sits at the 61st percentile, while the GTX 660 Ti sits at the 57th percentile. This means the HD 7790 outperforms a slightly larger share of the GPU field in its recorded benchmark, despite having a far smaller memory bus and fewer shading units. The GTX 660 Ti's average benchmark score is 15,063, which is 2,603 points lower than the HD 7790's single recorded score of 17,666. That is a 17.3% gap in raw recorded numbers, but again, these are different tests and should not be interpreted as a like-for-like comparison.

The nearest rival data offers additional context. The HD 7790's closest competitor is the NVIDIA GeForce RTX 4060, which scores 17,639, a delta of only 0.2% behind. The AMD Radeon 780M scores 17,588, a 0.4% gap, and the AMD Radeon Pro 560 scores 17,551, a 0.7% gap. On the other side, the NVIDIA Quadro RTX 4000 scores 17,789, which is 0.7% ahead of the HD 7790. These are remarkably tight margins, all within less than one percentage point. The HD 7790's 17,666 score places it in a cluster of modern GPUs and integrated graphics, which suggests that its recorded performance is competitive with much newer hardware in the Metal test.

For the GTX 660 Ti, the nearest rivals are all within a 1.5% band. The AMD Radeon Pro 560X scores 15,082, a 0.1% gap behind the GTX 660 Ti's average of 15,063. The AMD Radeon RX 7600 scores 15,171, which is 0.7% ahead. The NVIDIA GeForce RTX 3050 OEM scores 15,199, 0.9% ahead, and the AMD Radeon 680M scores 15,270, 1.4% ahead. The GTX 660 Ti's recorded performance is thus slightly below a cluster of modern mid-range and entry-level GPUs, but the differences are small, all under 1.5%. The data shows that both cards, despite their age, are still performing within a few percentage points of much more recent products in their respective benchmark categories.

Architecture Differences

The two cards come from different architectural families. The AMD Radeon HD 7790 uses the Bonaire chip based on GCN 2.0 architecture, belonging to the Southern Islands generation under the HD 7700 series. The NVIDIA GeForce GTX 660 Ti uses the GK104 chip based on Kepler architecture, from the GeForce 600 generation. Both are manufactured on a 28 nm process at TSMC, but the similarities end there.

The transistor counts differ substantially. The HD 7790 packs 2,080 million transistors on a 160 mm² die, giving a transistor density of 13.0 million per square millimeter. The GTX 660 Ti has 3,540 million transistors on a 294 mm² die, with a density of 12.0 million per square millimeter. The GTX 660 Ti's chip is nearly twice as large in area and carries 70% more transistors, but the HD 7790 achieves a slightly higher density, reflecting the newer GCN 2.0 design.

Memory configurations are a major point of divergence. The HD 7790 has 1024 MB of GDDR5 on a 128-bit bus, yielding 96.00 GB/s of bandwidth. The GTX 660 Ti doubles the memory to 2 GB, uses a 192-bit bus, and reaches 144.2 GB/s. That is a 50% bandwidth advantage for the GTX 660 Ti. Memory clocks are nearly identical: 1500 MHz for the HD 7790 versus 1502 MHz for the GTX 660 Ti, both effective at 6 Gbps.

Compute resources also favor the GTX 660 Ti heavily. It has 1344 shading units, 112 texture mapping units, and 24 ROPs. The HD 7790 has 896 shading units, 56 TMUs, and 16 ROPs. The GTX 660 Ti has 50% more shading units, exactly double the TMUs, and 50% more ROPs. This translates into higher theoretical rates: the GTX 660 Ti reaches 27.44 GPixel/s pixel rate and 109.8 GTexel/s texture rate, while the HD 7790 manages 16.00 GPixel/s and 56.00 GTexel/s. The GTX 660 Ti's FP32 throughput is 2.634 TFLOPS versus 1.792 TFLOPS for the HD 7790, a 47% advantage.

Clock behavior also differs. The GTX 660 Ti has a base clock of 915 MHz and a boost clock of 980 MHz. The HD 7790 has no recorded base or boost clock in the database. Power consumption is another differentiator: the GTX 660 Ti has a TDP of 150 W with a suggested PSU of 450 W and requires two 6-pin connectors. The HD 7790 has a TDP of 85 W, a suggested PSU of 250 W, and needs only one 6-pin connector.

API support shows a notable discrepancy. The HD 7790 supports DirectX 12 (12_0), while the GTX 660 Ti supports DirectX 12 (11_0), a lower feature level. Both support OpenGL 4.6 and Vulkan, though the GTX 660 Ti has a slightly newer Vulkan version (1.2.175 versus 1.2.170). Display outputs differ as well: the HD 7790 has 1x DVI, 1x HDMI 1.4a, and 2x mini-DisplayPort 1.2, while the GTX 660 Ti has 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2. Physical dimensions also vary, with the HD 7790 at 183 mm (7.2 inches) and the GTX 660 Ti at 241 mm (9.5 inches).

FAQ

Q: Which card has a higher recorded benchmark score?

A: The AMD Radeon HD 7790 has a single recorded Geekbench Metal score of 17,666. The NVIDIA GeForce GTX 660 Ti has an average benchmark score of 15,063, based on its Geekbench OpenCL score of 15,113 and Geekbench Vulkan score of 15,012. The HD 7790's score is higher, but the two cards were tested under different APIs.

Q: How much memory does each card have, and what is the bus width?

A: The AMD Radeon HD 7790 has 1024 MB of GDDR5 on a 128-bit bus, giving a bandwidth of 96.00 GB/s. The NVIDIA GeForce GTX 660 Ti has 2 GB of GDDR5 on a 192-bit bus, giving a bandwidth of 144.2 GB/s. The GTX 660 Ti has double the memory capacity and a 50% wider bus.

Q: What are the power requirements for each card?

A: The AMD Radeon HD 7790 has a TDP of 85 W, a suggested PSU of 250 W, and requires a single 6-pin power connector. The NVIDIA GeForce GTX 660 Ti has a TDP of 150 W, a suggested PSU of 450 W, and requires two 6-pin power connectors. The GTX 660 Ti consumes nearly twice the power.

Q: Do both cards support modern APIs?

A: Both cards support DirectX 12, OpenGL 4.6, and Vulkan, but at different levels. The HD 7790 supports DirectX 12 (12_0), while the GTX 660 Ti supports DirectX 12 (11_0). The GTX 660 Ti has a slightly newer Vulkan version (1.2.175 versus 1.2.170).

Q: How does each card rank among all GPUs?

A: The AMD Radeon HD 7790 ranks at the 61st percentile among all GPUs. The NVIDIA GeForce GTX 660 Ti ranks at the 57th percentile. The HD 7790 outperforms a larger share of the field in its recorded benchmark.

Q: What is the physical size difference between the two cards?

A: The AMD Radeon HD 7790 is 183 mm (7.2 inches) long. The NVIDIA GeForce GTX 660 Ti is 241 mm (9.5 inches) long. The GTX 660 Ti is significantly longer, which may affect case compatibility.

The Verdict

The data points to a clear split in strengths. The NVIDIA GeForce GTX 660 Ti is the more powerful card on paper, with 1344 shading units versus 896, 112 TMUs versus 56, 24 ROPs versus 16, and 2.634 TFLOPS FP32 versus 1.792 TFLOPS. Its memory subsystem is also superior: 2 GB versus 1024 MB, 192-bit versus 128-bit bus, and 144.2 GB/s versus 96.00 GB/s bandwidth. These are large advantages, ranging from 47% in FP32 to 100% in TMUs.

However, the AMD Radeon HD 7790 wins in the only recorded benchmark. Its Geekbench Metal score of 17,666 exceeds the GTX 660 Ti's average of 15,063 by 2,603 points, a 17.3% margin. The HD 7790 also ranks higher in the overall GPU distribution, at the 61st percentile versus the 57th percentile. The HD 7790 achieves this with far lower power consumption: 85 W versus 150 W TDP, and a suggested PSU of 250 W versus 450 W. It also supports a higher DirectX feature level (12_0 versus 11_0).

For a user prioritizing raw compute throughput, memory capacity, and bandwidth, the GTX 660 Ti is the stronger choice. Its 2 GB frame buffer and 144.2 GB/s bandwidth make it better suited for high-resolution textures and memory-intensive workloads. Its shading and texture resources are substantially higher, which should translate to better performance in GPU-bound tasks that leverage those units.

For a user prioritizing recorded benchmark performance, power efficiency, and modern API support, the HD 7790 is the better option. Its Metal score is higher, its percentile rank is better, and it delivers that performance at nearly half the power draw. The HD 7790 also has a smaller physical footprint, making it easier to fit in compact builds.

The data does not support a universal winner. The cards target different trade-offs, and the choice depends on which factors matter more. The GTX 660 Ti has the hardware muscle, while the HD 7790 has the recorded performance and efficiency.

Specification Differences

| Specification | AMD Radeon HD 7790 | NVIDIA GeForce GTX 660 Ti |

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

| Architecture | GCN 2.0 | Kepler |

| Generation | Southern Islands (HD 7700) | GeForce 600 |

| Transistors | 2,080 million | 3,540 million |

| Die Size | 160 mm² | 294 mm² |

| Transistor Density | 13.0M / mm² | 12.0M / mm² |

| Base Clock | Not recorded | 915 MHz |

| Boost Clock | Not recorded | 980 MHz |

| Memory Size | 1024 MB | 2 GB |

| Memory Bus | 128 bit | 192 bit |

| Memory Bandwidth | 96.00 GB/s | 144.2 GB/s |

| Shading Units | 896 | 1344 |

| TMUs | 56 | 112 |

| ROPs | 16 | 24 |

| Pixel Rate | 16.00 GPixel/s | 27.44 GPixel/s |

| Texture Rate | 56.00 GTexel/s | 109.8 GTexel/s |

| FP32 | 1.792 TFLOPS | 2.634 TFLOPS |

| TDP | 85 W | 150 W |

| Power Connectors | 1x 6-pin | 2x 6-pin |

| Suggested PSU | 250 W | 450 W |

| Display Outputs | 1x DVI, 1x HDMI 1.4a, 2x mini-DisplayPort 1.2 | 2x DVI, 1x HDMI 1.4a, 1x DisplayPort 1.2 |

| DirectX | 12 (12_0) | 12 (11_0) |

| Vulkan | 1.2.170 | 1.2.175 |

| Length | 183 mm (7.2 inches) | 241 mm (9.5 inches) |

| Launch MSRP | 149 USD | 299 USD |

Where Each One Wins

The NVIDIA GeForce GTX 660 Ti wins in every raw compute category. It has more shading units, more TMUs, more ROPs, higher pixel rate, higher texture rate, and higher FP32 throughput. It also has double the memory capacity, a wider memory bus, and 50% more memory bandwidth. These advantages make it the clear choice for workloads that scale with these resources, such as high-resolution rendering, texture-heavy scenes, and compute tasks that can utilize its 1344 shading units.

The AMD Radeon HD 7790 wins in recorded benchmark performance. Its Geekbench Metal score of 17,666 is 2,603 points higher than the GTX 660 Ti's average of 15,063. It also ranks at the 61st percentile versus the 57th percentile, meaning it outperforms a larger share of the GPU population. The HD 7790 wins on power efficiency, with an 85 W TDP versus 150 W, and a suggested PSU of 250 W versus 450 W. It also supports a higher DirectX feature level (12_0 versus 11_0) and is substantially shorter, at 183 mm versus 241 mm.

The GTX 660 Ti also leads in API version for Vulkan, with 1.2.175 versus 1.2.170, and offers two DVI outputs instead of one. The HD 7790 offers two mini-DisplayPort outputs instead of one DisplayPort, which may be relevant for multi-monitor setups. The GTX 660 Ti's launch MSRP was 299 USD, while the HD 7790's was 149 USD, but pricing should not factor into the analysis beyond stating these recorded values.

For users who need maximum memory bandwidth and compute throughput, the GTX 660 Ti is the superior product. For users who prioritize the single recorded benchmark, power draw, and a smaller card footprint, the HD 7790 is the better fit. The data does not show one card dominating the other across all metrics; instead, it shows two designs with different strengths, and the choice depends on the specific workload and system constraints.