NVIDIA GeForce GTX 1660 Ti vs NVIDIA GeForce GTX 680M Comparison

The NVIDIA GeForce GTX 1660 Ti and the NVIDIA GeForce GTX 680M represent two distinct eras of mobile and desktop GPU design. The data shows a single head-to-head benchmark result, but the specification sheets and overall benchmark averages paint a comprehensive picture of generational progress. The GTX 1660 Ti, built on the Turing architecture, is a modern desktop part, while the GTX 680M is a Kepler-based mobile module from an earlier generation.

Head-to-Head Benchmarks

The only directly comparable benchmark between the two GPUs is Geekbench OpenCL. In this test, the results are decisively lopsided. The GTX 1660 Ti scores 51,029 points, while the GTX 680M manages only 9,230 points. This translates to a delta of 452.9%, meaning the GTX 1660 Ti is roughly four and a half times faster in this compute-oriented workload. This is not a marginal victory; it is a dominant performance gap that highlights the massive improvement in raw compute throughput between the two generations.

Looking at the broader benchmark data, the GTX 1660 Ti has an average benchmark score of 7,723 across all its tested workloads. This places it in the 41st percentile of all GPUs in the database. Its nearest rivals, based on average score, include the AMD Radeon 540 (7,673, a 0.7% difference), the AMD Radeon Pro WX 3100 (7,580, a 1.9% difference), and the AMD Radeon R7 250 (7,557, a 2.2% difference). This indicates that while the GTX 1660 Ti is not a top-tier card, it sits in a competitive mid-range bracket.

In contrast, the GTX 680M has an average benchmark score of 7,023, placing it in the 39th percentile of all GPUs. Its closest rival is the NVIDIA T600, which scores 7,035, putting the GTX 680M just 0.2% behind it. Other rivals include the AMD Radeon R5 M240 (6,975, a 0.7% difference) and the NVIDIA GeForce GTX 675M (6,946, a 1.1% difference). Interestingly, the GTX 680M is also compared to the NVIDIA GeForce GTX 970, which scores 7,157, putting the GTX 680M 1.9% behind that much newer desktop part.

The difference in average scores is 700 points, which is a 10% advantage for the GTX 1660 Ti. However, this aggregate figure masks the true scale of the performance gap. The Geekbench OpenCL result shows that in compute-heavy tasks, the newer architecture is in a completely different league. While the GTX 680M holds its own in aggregate against its own rivals, it cannot compete with the sheer computational power of the GTX 1660 Ti.

The Verdict

From the data, the choice is clear for most users: the GTX 1660 Ti is the superior performer. Its 452.9% lead in the Geekbench OpenCL test and its higher average benchmark score (7,723 vs 7,023) demonstrate a significant generational leap. The GTX 1660 Ti is the better option for anyone prioritizing compute performance in modern applications.

The GTX 680M, however, has its own niche. Its data is limited to two benchmarks (Geekbench Metal and Geekbench OpenCL), and its performance profile is that of a mobile part from 2012. Its average score of 7,023 is respectable for its era, but it is simply outclassed by the newer Turing card. Its 39th percentile ranking, while close to the GTX 1660 Ti's 41st, does not reflect the massive gap in compute capabilities.

For a user building or upgrading a desktop system, the GTX 1660 Ti is the only logical choice based on this data. For someone with an older laptop that uses an MXM module, the GTX 680M is the only one of the two that fits that form factor. The data suggests that the GTX 1660 Ti is the definitive winner in raw performance, while the GTX 680M is a legacy part that remains relevant only in its specific mobile context.

Architecture Differences

The two GPUs are built on fundamentally different architectures, which explains their performance disparity. The GTX 1660 Ti uses the TU116 chip based on the Turing architecture, fabricated on a 12 nm process at TSMC. It contains 6,600 million transistors on a die size of 284 mm², resulting in a transistor density of 23.2M per mm². In contrast, the GTX 680M uses the GK104 chip based on the much older Kepler architecture, also fabricated at TSMC but on a 28 nm process. It packs 3,540 million transistors on a larger die of 294 mm², yielding a much lower transistor density of 12.0M per mm².

The clock speeds also show a stark difference. The GTX 1660 Ti has a base clock of 1500 MHz and a boost clock of 1770 MHz. The GTX 680M is significantly slower, with a base clock of 719 MHz and a boost clock of 758 MHz. This clock speed advantage, combined with the architectural improvements in Turing, contributes heavily to the performance gap.

Memory technology has also evolved. The GTX 1660 Ti uses 6 GB of GDDR6 memory on a 192-bit bus, with a memory clock of 1500 MHz (12 Gbps effective) and a bandwidth of 288.0 GB/s. The GTX 680M has 4 GB of GDDR5 memory on a wider 256-bit bus, but a much slower memory clock of 900 MHz (3.6 Gbps effective), resulting in a bandwidth of just 115.2 GB/s. The newer card's memory bandwidth is more than double that of the older one.

The feature sets also differ. The GTX 1660 Ti supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The GTX 680M supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. While both support DirectX 12, the feature level is higher on the newer card. Neither card has ray tracing or tensor cores. The GTX 1660 Ti has a dual-slot form factor with a 1x 8-pin power connector and a suggested PSU of 300 W, while the GTX 680M is an MXM module with no power connectors.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The NVIDIA GeForce GTX 1660 Ti has a higher average benchmark score of 7,723, compared to the NVIDIA GeForce GTX 680M's 7,023.

Q: What is the performance difference in the Geekbench OpenCL test?

A: The GTX 1660 Ti scores 51,029, which is 452.9% higher than the GTX 680M's score of 9,230.

Q: Which GPU has a higher memory bandwidth?

A: The GTX 1660 Ti has a memory bandwidth of 288.0 GB/s, which is significantly higher than the GTX 680M's 115.2 GB/s.

Q: What is the transistor density of each GPU?

A: The GTX 1660 Ti has a transistor density of 23.2M / mm², while the GTX 680M has a lower density of 12.0M / mm².

Q: Which GPU supports a newer version of Vulkan?

A: The GTX 1660 Ti supports Vulkan 1.4, while the GTX 680M supports Vulkan 1.2.175.

Q: Which GPU has a higher boost clock?

A: The GTX 1660 Ti has a boost clock of 1770 MHz, which is much higher than the GTX 680M's boost clock of 758 MHz.

Where Each One Wins

The GTX 1660 Ti wins decisively in compute-heavy workloads, as evidenced by the Geekbench OpenCL result. Its higher pixel rate (84.96 GPixel/s vs 21.22 GPixel/s), texture rate (169.9 GTexel/s vs 84.90 GTexel/s), and FP32 throughput (5.437 TFLOPS vs 2.038 TFLOPS) make it the clear choice for modern gaming and rendering tasks. It also has a higher FP16 performance of 10.87 TFLOPS (2:1), a feature entirely absent from the GTX 680M.

The GTX 680M has no benchmark wins in the head-to-head data. However, its only advantage lies in its physical form factor. As an MXM module with a 100 W TDP and no power connectors, it is designed for portable devices where space and power are at a premium. The GTX 1660 Ti, with its dual-slot design and 1x 8-pin power connector, requires a desktop chassis or a large laptop chassis that can accommodate its 120 W TDP and cooling needs.

In terms of raw specifications, the GTX 1660 Ti has more shading units (1536 vs 1344) and more ROPs (48 vs 32), though the GTX 680M has more TMUs (112 vs 96). The GTX 1660 Ti also has a larger memory capacity (6 GB vs 4 GB) and a faster memory type (GDDR6 vs GDDR5). The GTX 680M does have a wider memory bus (256-bit vs 192-bit), but this is offset by the much slower memory clock.

Specification Differences

The specification sheets for the two GPUs show differences in nearly every category. The GTX 1660 Ti is based on a 12 nm process, while the GTX 680M uses a 28 nm process. The GTX 1660 Ti has 6,600 million transistors, compared to 3,540 million for the GTX 680M. The die size is 284 mm² for the newer card and 294 mm² for the older one.

Clock speeds differ substantially: the GTX 1660 Ti has a base clock of 1500 MHz and a boost clock of 1770 MHz, while the GTX 680M has a base clock of 719 MHz and a boost clock of 758 MHz. The memory configuration also differs, with the GTX 1660 Ti using 6 GB of GDDR6 on a 192-bit bus, and the GTX 680M using 4 GB of GDDR5 on a 256-bit bus.

Compute rates show the newer card's advantage: the GTX 1660 Ti has a pixel rate of 84.96 GPixel/s and a texture rate of 169.9 GTexel/s, while the GTX 680M has 21.22 GPixel/s and 84.90 GTexel/s, respectively. The FP32 performance is 5.437 TFLOPS for the GTX 1660 Ti and 2.038 TFLOPS for the GTX 680M.

Power and physical specifications also vary. The GTX 1660 Ti has a TDP of 120 W, is a dual-slot card, and requires a 1x 8-pin power connector and a 300 W suggested PSU. The GTX 680M has a TDP of 100 W, is an MXM module, and has no power connectors. The bus interface is PCIe 3.0 x16 for the GTX 1660 Ti, while the GTX 680M uses MXM-B (3.0). The GTX 1660 Ti's display outputs include 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a, while the GTX 680M's outputs are listed as "Portable Device Dependent."