NVIDIA GeForce GTX 1080 Ti vs NVIDIA GeForce GTX 770 Comparison

The GeForce GTX 1080 Ti and the GeForce GTX 770 are both end-of-life NVIDIA cards, but they belong to different eras. The data shows a complete generational shift. The GTX 1080 Ti wins every single head-to-head benchmark in this comparison, and wins decisively. The GTX 770 is a capable card for its time, but the GTX 1080 Ti is in a different performance class entirely. This comparison is less about which card is better and more about understanding the magnitude of the performance gap between a high-end Pascal card and a mid-range Kepler card.

The Verdict

The choice, based strictly on the benchmark data, is unambiguous: the NVIDIA GeForce GTX 1080 Ti is the superior product. It outperforms the GTX 770 by a massive margin in every test where both were measured. The GTX 1080 Ti achieves an average benchmark score of 15548, while the GTX 770 trails at 14747. While this average delta seems small, the specific head-to-head tests tell a much different story.

If you are looking at these two cards for a modern system, the GTX 1080 Ti is the only rational pick. Its performance is orders of magnitude ahead, making it suitable for high-resolution gaming and compute tasks that would cripple the GTX 770. The GTX 770, with its 2 GB of memory and older architecture, is only relevant for legacy systems or very light, older workloads. In short, the GTX 1080 Ti is a high-performance card that can still handle modern demands, while the GTX 770 is a relic best suited for a basic display output or a retro build. The GTX 1080 Ti sits in the 58th percentile of all GPUs, versus the 57th percentile for the GTX 770, but the head-to-head deltas show the true gulf in class.

Where Each One Wins

The GTX 1080 Ti wins in every category where data is available. There are zero benchmark wins for the GTX 770 in the head-to-head comparison. The GTX 1080 Ti’s wins are not marginal; they are overwhelming.

The GTX 1080 Ti is the clear winner for any modern gaming scenario, particularly at high resolutions or with demanding graphical settings. Its superior compute performance also makes it the choice for GPU-accelerated tasks. The GTX 770 does not win in any measurable workload in this data set. Its only theoretical advantage is that it can still run older DirectX 11 and 12 titles at lower settings, but it lacks the hardware resources to handle anything modern. Where the GTX 770 might be considered is in a purely secondary or legacy role, where its lower power draw and smaller footprint are non-factors. For any use case that requires actual graphics processing, the GTX 1080 Ti is the definitive winner.

Architecture Differences

The two cards are built on fundamentally different architectures, nodes, and process technologies. The GTX 1080 Ti is based on the Pascal architecture, using the GP102 chip, manufactured on a 16 nm process at TSMC. The GTX 770 uses the older Kepler architecture, with the GK104 chip, built on a 28 nm process. This process shrink is a major factor in the performance difference, allowing the GTX 1080 Ti to pack 11,800 million transistors into a 471 mm² die, resulting in a transistor density of 25.1M / mm². In contrast, the GTX 770 has 3,540 million transistors on a 294 mm² die, for a density of 12.0M / mm².

The memory subsystems are also vastly different. The GTX 1080 Ti uses 11 GB of GDDR5X memory on a 352-bit bus, delivering a bandwidth of 484.4 GB/s. The GTX 770 has 2 GB of GDDR5 on a 256-bit bus, with a bandwidth of 224.4 GB/s. This means the GTX 1080 Ti has more than double the memory bandwidth and over five times the memory capacity, which is critical for modern games and high-resolution textures.

The compute resources are equally disparate. The GTX 1080 Ti has 3584 shading units, 224 texture mapping units (TMUs), and 88 render output units (ROPs). The GTX 770 has 1536 shading units, 128 TMUs, and 32 ROPs. This translates to a pixel rate of 139.2 GPixel/s and a texture rate of 354.4 GTexel/s for the GTX 1080 Ti, versus 34.72 GPixel/s and 138.9 GTexel/s for the GTX 770. The FP32 performance is 11.34 TFLOPS for the GTX 1080 Ti versus 3.333 TFLOPS for the GTX 770. The GTX 1080 Ti also supports FP16 at 177.2 GFLOPS, while the GTX 770 has no listed FP16 capability. In terms of API support, the GTX 1080 Ti supports DirectX 12 (12_1), while the GTX 770 is limited to DirectX 12 (11_0). Both support OpenGL 4.6, but the GTX 1080 Ti supports Vulkan 1.4, while the GTX 770 supports Vulkan 1.2.175.

FAQ

Q: Is the GTX 1080 Ti worth considering over the GTX 770 in 2024?

A: Yes. The benchmark data shows the GTX 1080 Ti is overwhelmingly faster, with a 226.9% lead in Geekbench Metal, a 332.5% lead in Geekbench OpenCL, and a 111.4% lead in Geekbench Vulkan. It is in a completely different performance class.

Q: Can the GTX 770 handle modern games?

A: The data does not support this. The GTX 770 only has 2 GB of memory and a much lower compute capability. Its average benchmark score of 14747 is only 5% lower than the GTX 1080 Ti's average, but this is misleading because the head-to-head tests show a massive gap. Its DirectX 12 (11_0) support also limits its compatibility with modern titles.

Q: Which card has better memory bandwidth?

A: The GTX 1080 Ti has a bandwidth of 484.4 GB/s, which is more than double the GTX 770's 224.4 GB/s. This is a critical advantage for high-resolution textures and memory-intensive workloads.

Q: Are these cards still supported by current drivers?

A: Both are listed as end-of-life products. However, the GTX 1080 Ti supports newer API versions, including Vulkan 1.4 and DirectX 12 (12_1), suggesting better long-term software support compared to the GTX 770's Vulkan 1.2.175 and DirectX 12 (11_0).

Q: What is the difference in their power requirements?

A: The GTX 1080 Ti has a TDP of 250 W and a suggested PSU of 600 W, while the GTX 770 has a TDP of 230 W and a suggested PSU of 550 W. Both require a 1x 6-pin + 1x 8-pin power connector setup.

Q: Is the GTX 770 a good card for a budget build?

A: Based on the performance data, it is not recommended. The GTX 770's performance is vastly inferior to the GTX 1080 Ti in every head-to-head test. While it may be cheaper, its lack of performance and memory capacity makes it a poor choice for any modern workload.

Head-to-Head Benchmarks

The head-to-head benchmark results are stark. The GTX 1080 Ti wins all three tests, and the deltas are enormous. The largest win for the GTX 1080 Ti comes in the Geekbench OpenCL test. Here, the GTX 1080 Ti scores 67929, while the GTX 770 scores 15707. This is a delta of 332.5%, meaning the GTX 1080 Ti is over four times faster in this compute-oriented workload. This is a clear indicator of the massive difference in raw compute power, driven by the 11.34 TFLOPS FP32 performance versus the 3.333 TFLOPS of the GTX 770.

In the Geekbench Metal test, the GTX 1080 Ti scores 30624, compared to the GTX 770's 9369. This represents a 226.9% advantage for the GTX 1080 Ti. This test is relevant for Apple's Metal API, but it also reflects general GPU compute capabilities. The GTX 1080 Ti is more than three times faster here.

The smallest delta of the three is in the Geekbench Vulkan test, but it is still a dominant win for the GTX 1080 Ti. It scores 40511, while the GTX 770 scores 19166, a 111.4% advantage. This means the GTX 1080 Ti is more than twice as fast in this cross-platform graphics API. This is a significant margin, especially considering that Vulkan is a low-overhead API that can often reduce the gap between different hardware. The fact that the GTX 1080 Ti still doubles the GTX 770's score shows the sheer hardware advantage it holds.

These results paint a clear picture. The GTX 1080 Ti is not just slightly better; it is a generational leap ahead. The GTX 770 is simply outclassed in every measurable way, and the GTX 1080 Ti's wins are so large that they are not just improvements, but complete overhauls of the performance envelope.

Specification Differences

The specification differences between the two cards are extensive and explain the performance gap. The GTX 1080 Ti is built on a 16 nm process, while the GTX 770 uses a 28 nm process. The GTX 1080 Ti uses the GP102 chip, while the GTX 770 uses the GK104. The transistor count is 11,800 million for the GTX 1080 Ti versus 3,540 million for the GTX 770, and the die size is 471 mm² versus 294 mm². This leads to a transistor density of 25.1M / mm² for the GTX 1080 Ti and 12.0M / mm² for the GTX 770.

Clock speeds are also different. The GTX 1080 Ti has a base clock of 1481 MHz and a boost clock of 1582 MHz, with memory running at 1376 MHz (11 Gbps effective). The GTX 770 has a base clock of 1046 MHz and a boost clock of 1085 MHz, with memory at 1753 MHz (7 Gbps effective). While the GTX 770 has a higher memory clock, the GTX 1080 Ti's much wider 352-bit memory bus versus the 256-bit bus of the GTX 770 gives it the massive bandwidth advantage.

The memory configuration is a major differentiator. The GTX 1080 Ti has 11 GB of GDDR5X, while the GTX 770 has 2 GB of GDDR5. The shading units are 3584 versus 1536, the TMUs are 224 versus 128, and the ROPs are 88 versus 32. The pixel rate is 139.2 GPixel/s versus 34.72 GPixel/s, and the texture rate is 354.4 GTexel/s versus 138.9 GTexel/s. The FP32 compute is 11.34 TFLOPS versus 3.333 TFLOPS. The GTX 1080 Ti has FP16 capability at 177.2 GFLOPS (1:64), while the GTX 770 has no listed FP16 performance. The TDP is 250 W for the GTX 1080 Ti and 230 W for the GTX 770, with a suggested PSU of 600 W and 550 W respectively. Both are dual-slot cards with the same length of 267 mm, but the GTX 1080 Ti is slightly wider at 40 mm versus 38 mm. The GTX 1080 Ti has different display outputs: 1x HDMI 2.0 and 3x DisplayPort 1.4a, while the GTX 770 has 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2. The API support also differs, with the GTX 1080 Ti supporting DirectX 12 (12_1) and Vulkan 1.4, while the GTX 770 supports DirectX 12 (11_0) and Vulkan 1.2.175. Both support OpenGL 4.6.