NVIDIA GeForce GTX 1660 SUPER vs NVIDIA GeForce GTX 770 Comparison

The NVIDIA GeForce GTX 770 and the NVIDIA GeForce GTX 1660 SUPER represent two distinct eras of NVIDIA’s GPU lineup. The GTX 770, a Kepler-based card from the GeForce 700 generation, was once a high-end part, while the GTX 1660 SUPER, a Turing-based card from the GeForce 16 series, arrived years later as a mid-range offering. The benchmark data from the database shows a clear overall winner: the GTX 1660 SUPER wins both recorded head-to-head tests by substantial margins. However, the story is more nuanced than a simple victory, as the two cards differ profoundly in architecture, memory configuration, and power efficiency.

Head-to-Head Benchmarks

The database records two direct benchmark comparisons between these cards, and the GTX 1660 SUPER dominates both. In the Geekbench OpenCL test, the GTX 770 scores 15,707 points, while the GTX 1660 SUPER scores 52,490 points. That is a delta of 70.1% in favor of the newer card, meaning the GTX 1660 SUPER delivers roughly three and a half times the compute performance in this workload. The margin is staggering, and it reflects not just a generational leap in raw compute, but also the architectural efficiency of Turing over Kepler.

The second head-to-head test, Geekbench Vulkan, tells a similar story. The GTX 770 manages 19,166 points, while the GTX 1660 SUPER reaches 57,102 points. The delta here is 66.4% in favor of the GTX 1660 SUPER. This result indicates that the newer card is particularly strong in modern graphics APIs, which rely on lower-level hardware control and more efficient thread scheduling. The GTX 770, despite being a capable card in its day, simply cannot keep up with the Turing architecture’s Vulkan implementation.

In terms of overall average benchmark score, the GTX 770 actually appears higher at 14,747 points, compared to the GTX 1660 SUPER’s 12,986 points. This counterintuitive result is explained by the different benchmark suites available for each card. The GTX 770’s average is drawn from its three Geekbench tests (Metal, OpenCL, and Vulkan), while the GTX 1660 SUPER’s average includes a broader set of Passmark tests, which may weight different workloads. The head-to-head data, which uses identical tests, is the more reliable indicator of relative performance, and it clearly favors the GTX 1660 SUPER.

The GTX 770’s nearest rivals in the database include the AMD Radeon RX 5500 XT, which scores 14,692 points, a delta of only 0.4% from the GTX 770. The NVIDIA Quadro M2000 scores 14,532 points, just 1.5% behind. On the other side, the GTX 660 Ti scores 15,063 points, putting it 2.1% ahead of the GTX 770, and the AMD Radeon Pro 560X scores 15,082 points, 2.2% ahead. The GTX 1660 SUPER’s rivals include the NVIDIA GeForce RTX 3050 Ti Mobile at 12,940 points (0.4% behind), the AMD Radeon RX 580 at 12,928 points (0.4% behind), and the AMD Radeon 740M at 12,870 points (0.9% behind). The GTX 1660 SUPER sits slightly above these cards in its average score, while the GTX 770 sits in the middle of its peer group.

Architecture Differences

The two cards are built on fundamentally different architectures. The GTX 770 uses the GK104 chip, based on Kepler, and is manufactured on a 28 nm process at TSMC. The chip contains 3,540 million transistors on a die size of 294 mm², yielding a transistor density of 12.0 million transistors per square millimeter. In contrast, the GTX 1660 SUPER uses the TU116 chip, based on Turing, and is built on a 12 nm process, also at TSMC. This chip packs 6,600 million transistors into a slightly smaller die of 284 mm², giving a much higher density of 23.2 million transistors per square millimeter. The shift from 28 nm to 12 nm is the primary driver of the GTX 1660 SUPER’s efficiency and performance advantage.

Clock speeds also differ significantly. The GTX 770 runs at a base clock of 1,046 MHz and a boost clock of 1,085 MHz. The GTX 1660 SUPER runs much higher, with a base clock of 1,530 MHz and a boost clock of 1,785 MHz. This higher clock speed, combined with the architectural improvements, explains why the GTX 1660 SUPER achieves 5.027 TFLOPS of FP32 compute, compared to 3.333 TFLOPS for the GTX 770. The GTX 1660 SUPER also supports FP16 compute at 10.05 TFLOPS with a 2:1 ratio, a feature the GTX 770 lacks entirely.

The memory subsystems are another major point of divergence. The GTX 770 has 2 GB of GDDR5 memory on a 256-bit bus, providing 224.4 GB/s of bandwidth. The GTX 1660 SUPER has 6 GB of GDDR6 memory on a 192-bit bus, providing 336.0 GB/s of bandwidth. The wider bus on the GTX 770 is offset by the much faster GDDR6 memory on the GTX 1660 SUPER, which runs at 14 Gbps effective, compared to 7 Gbps effective on the GTX 770. The GTX 1660 SUPER’s larger memory capacity is also critical for modern games and applications, which often require more than 2 GB of VRAM.

Pixel and texture rates further illustrate the gap. The GTX 770 offers a pixel rate of 34.72 GPixel/s and a texture rate of 138.9 GTexel/s. The GTX 1660 SUPER delivers a pixel rate of 85.68 GPixel/s and a texture rate of 157.1 GTexel/s. The GTX 1660 SUPER has fewer shading units (1,408 vs. 1,536) and fewer texture mapping units (88 vs. 128), but it compensates with higher clock speeds and more ROPs (48 vs. 32). The result is a card that is significantly faster in both pixel fill and texture processing.

FAQ

Q: Which card has more compute power?

A: The GTX 1660 SUPER has significantly more compute power. Its FP32 throughput is 5.027 TFLOPS, compared to 3.333 TFLOPS for the GTX 770. In the Geekbench OpenCL test, the GTX 1660 SUPER scores 52,490 points versus 15,707 points for the GTX 770.

Q: How does memory capacity compare?

A: The GTX 1660 SUPER has 6 GB of GDDR6 memory, while the GTX 770 has 2 GB of GDDR5 memory. The GTX 1660 SUPER also has higher memory bandwidth at 336.0 GB/s, compared to 224.4 GB/s for the GTX 770.

Q: What are the power requirements for each card?

A: The GTX 770 has a TDP of 230 W and requires a 550 W power supply, with one 6-pin and one 8-pin power connector. The GTX 1660 SUPER has a TDP of 125 W, requires a 300 W power supply, and uses a single 8-pin connector.

Q: Which card supports newer display outputs?

A: The GTX 1660 SUPER supports HDMI 2.0 and DisplayPort 1.4a, while the GTX 770 supports HDMI 1.4a and DisplayPort 1.2. Both cards include a DVI output.

Q: How do the APIs compare?

A: The GTX 770 supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. The GTX 1660 SUPER supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The GTX 1660 SUPER’s higher DirectX feature level and newer Vulkan version provide better support for modern titles.

Q: What is the transistor density difference?

A: The GTX 770 has a transistor density of 12.0 million per square millimeter, while the GTX 1660 SUPER has a density of 23.2 million per square millimeter. This reflects the newer 12 nm manufacturing process used for the GTX 1660 SUPER, compared to the 28 nm process for the GTX 770.

Specification Differences

The two cards differ in nearly every core specification. The GTX 770 uses the GK104 chip with 1,536 shading units, 128 TMUs, and 32 ROPs. The GTX 1660 SUPER uses the TU116 chip with 1,408 shading units, 88 TMUs, and 48 ROPs. The GTX 1660 SUPER has fewer shading units and TMUs, but more ROPs. Clock speeds are far higher on the GTX 1660 SUPER: base 1,530 MHz and boost 1,785 MHz, versus base 1,046 MHz and boost 1,085 MHz for the GTX 770.

Memory is a major differentiator. The GTX 770 has 2 GB of GDDR5 on a 256-bit bus with 224.4 GB/s bandwidth. The GTX 1660 SUPER has 6 GB of GDDR6 on a 192-bit bus with 336.0 GB/s bandwidth. The effective memory clock is 7 Gbps for the GTX 770 and 14 Gbps for the GTX 1660 SUPER.

Power and physical specs also differ. The GTX 770 has a TDP of 230 W, a suggested power supply of 550 W, and uses 1x 6-pin plus 1x 8-pin connectors. The GTX 1660 SUPER has a TDP of 125 W, a suggested power supply of 300 W, and uses a single 8-pin connector. The GTX 770 is 267 mm long, 111 mm high, and 38 mm wide. The GTX 1660 SUPER is 229 mm long, 111 mm high, and 35 mm wide. Both are dual-slot cards.

The process node is 28 nm for the GTX 770 and 12 nm for the GTX 1660 SUPER. Transistor count is 3,540 million for the GTX 770 versus 6,600 million for the GTX 1660 SUPER. Die size is 294 mm² for the GTX 770 and 284 mm² for the GTX 1660 SUPER. The GTX 770 supports DirectX 12 (11_0) and Vulkan 1.2.175, while the GTX 1660 SUPER supports DirectX 12 (12_1) and Vulkan 1.4. Display outputs are also different: the GTX 770 has 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2, while the GTX 1660 SUPER has 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a.

Where Each One Wins

The GTX 1660 SUPER wins decisively in compute-heavy and modern API workloads. Its Geekbench OpenCL score of 52,490 points is over three times the GTX 770’s 15,707 points. Its Geekbench Vulkan score of 57,102 points is nearly three times the GTX 770’s 19,166 points. These wins make the GTX 1660 SUPER the clear choice for tasks that leverage OpenCL or Vulkan, such as GPU-accelerated rendering, scientific computing, and current-generation games that use Vulkan.

The GTX 1660 SUPER also wins on efficiency. Its TDP of 125 W is nearly half the GTX 770’s 230 W, and it requires a much smaller power supply (300 W vs. 550 W). This makes it a better fit for compact or pre-built systems with limited power headroom. The GTX 1660 SUPER’s 6 GB of memory is also a significant advantage for modern workloads, as 2 GB on the GTX 770 is often insufficient for high-resolution textures or large datasets.

The GTX 770 does not win any recorded benchmark tests. Its only advantage lies in its higher average benchmark score of 14,747 points, which is driven by its Geekbench Metal score of 9,369 points, a test that the GTX 1660 SUPER does not have recorded. This suggests that the GTX 770 may be competitive in Apple Metal environments, but the data does not support a broader performance win. The GTX 770’s higher transistor count per die area (12.0M vs. 23.2M per mm²) is not a performance metric and does not translate into any measured advantage.

The Verdict

The data is unambiguous: the GTX 1660 SUPER is the superior card for nearly all use cases. It wins both head-to-head benchmarks by margins of 70.1% and 66.4%, respectively, and offers higher compute throughput, more memory, lower power consumption, and newer API support. The GTX 770’s only claim to relevance is its legacy Metal performance and its position in the database’s average score, which is skewed by an incomplete benchmark suite.

For users seeking a card for modern gaming, compute workloads, or any application that benefits from Vulkan or OpenCL, the GTX 1660 SUPER is the obvious choice. Its 6 GB of GDDR6 memory provides future-proofing that the GTX 770’s 2 GB cannot match. Its lower TDP and power supply requirement make it easier to integrate into existing systems. Its higher pixel rate of 85.68 GPixel/s and texture rate of 157.1 GTexel/s ensure strong performance in graphics-intensive tasks.

The GTX 770 is an end-of-life product from 2013, and the GTX 1660 SUPER, though also end-of-life, is from 2019. Both are legacy parts, but the GTX 1660 SUPER represents a much more capable and efficient design. The database’s percentile ranking places the GTX 770 in the 57th percentile of all GPUs, while the GTX 1660 SUPER sits in the 53rd percentile, but this ranking uses different benchmark sets and should not be interpreted as a performance comparison. In direct head-to-head testing, the GTX 1660 SUPER wins every time. Users should pick the GTX 1660 SUPER unless they have a specific requirement for the GTX 770’s unique features, such as its dual DVI outputs or its Metal benchmark performance.