NVIDIA GeForce GTX 1660 SUPER vs NVIDIA GeForce GTX 780M Comparison

The GeForce GTX 1660 SUPER and the GeForce GTX 780M represent two very different eras of NVIDIA mobile and desktop graphics. The GTX 780M was a high-end notebook part from the Kepler generation, while the GTX 1660 SUPER is a desktop Turing-based card. The database shows a clear overall winner, but the specifics of how each card achieves its results are worth examining for anyone considering an older laptop versus a modern entry-level desktop setup.

Where Each One Wins

The GTX 1660 SUPER wins every recorded head-to-head benchmark. In the two tests where both cards have results, the Geekbench OpenCL score for the 1660 SUPER is 52490 against 12769 for the 780M, a delta of 311.1%. In Geekbench Vulkan, the 1660 SUPER scores 57102, while the 780M manages 12696, a delta of 349.8%. There is no category in the recorded data where the 780M comes out ahead.

The GTX 1660 SUPER also holds a significant advantage in the broader benchmark suite. Its average benchmark score is 12986, which places it at the 53rd percentile of all GPUs in the database. The GTX 780M has an average score of 11261, good for the 50th percentile. While both cards sit near the middle of the overall distribution, the 1660 SUPER is consistently faster across all recorded workloads.

For specific API tests, the 1660 SUPER shows a wide range of performance. It scores 12699 in Passmark G3D, 5076 in Passmark GPU Compute, and 189 in Passmark DirectX 9. The 780M simply has no recorded results for those tests, so its strengths, if any, are not visible in the database. The 1660 SUPER also has a higher pixel rate at 85.68 GPixel/s versus 25.50 GPixel/s for the 780M, and a texture rate of 157.1 GTexel/s versus 102.0 GTexel/s. The 780M is not competitive in any measured category.

Architecture Differences

The two GPUs are built on fundamentally different architectures. The GTX 1660 SUPER uses the TU116 chip based on the Turing architecture, manufactured on a 12 nm process at TSMC. The GTX 780M uses the GK104 chip based on the much older Kepler architecture, also from TSMC but on a 28 nm process. This process difference explains a great deal of the performance gap.

Transistor counts tell the story of complexity. The 1660 SUPER packs 6,600 million transistors into a die size of 284 mm², giving it a transistor density of 23.2M per mm². The 780M has 3,540 million transistors on a larger die of 294 mm², with a density of 12.0M per mm². The newer process allows the 1660 SUPER to fit nearly twice the transistors into a slightly smaller die.

Clock speeds are also drastically different. The 1660 SUPER has a base clock of 1530 MHz and a boost clock of 1785 MHz. The 780M is much slower with a base of 771 MHz and a boost of 797 MHz. The 1660 SUPER also benefits from faster memory: it uses 6 GB of GDDR6 at 1750 MHz with an effective rate of 14 Gbps, while the 780M uses 4 GB of GDDR5 at 1250 MHz with 5 Gbps effective. The memory bus width favors the 780M at 256 bit versus 192 bit for the 1660 SUPER, but the newer memory technology gives the 1660 SUPER a massive bandwidth advantage of 336.0 GB/s versus 160.0 GB/s.

The shading core counts are close, with the 780M having 1536 shading units and the 1660 SUPER having 1408. The 780M also has more texture mapping units at 128 versus 88. However, the 1660 SUPER has more ROPs at 48 versus 32, and its much higher clocks more than compensate for the lower core counts. The 1660 SUPER also supports Vulkan 1.4, while the 780M only reaches Vulkan 1.2.175, and DirectX 12 (12_1) versus DirectX 12 (11_0) for the 780M.

Head-to-Head Benchmarks

The two Geekbench tests are the only direct comparisons available. In Geekbench OpenCL, the 1660 SUPER scores 52490 against 12769 for the 780M, a delta of 311.1%. This is a massive margin that reflects both the architectural improvements and the clock speed advantage. The 1660 SUPER is more than four times faster in this compute workload.

In Geekbench Vulkan, the gap is even wider. The 1660 SUPER scores 57102, while the 780M scores 12696, a delta of 349.8%. Vulkan is a modern API that scales well with the 1660 SUPER's newer architecture. The 780M's older Kepler design was not built with modern compute APIs in mind, and the results show it.

The broader benchmark data reinforces this picture. The 1660 SUPER has an average benchmark score of 12986, which is 15.3% higher than the 780M's 11261. The 1660 SUPER also has a higher Passmark G3D score of 12699, a Passmark GPU Compute score of 5076, and a Passmark DirectX 12 score of 50. The 780M has no recorded scores for these tests, so direct comparisons are impossible, but the Geekbench results are decisive.

The 1660 SUPER also has a significant advantage in raw throughput. Its FP32 performance is 5.027 TFLOPS, more than double the 780M's 2.448 TFLOPS. The 1660 SUPER also supports FP16 at 10.05 TFLOPS with a 2:1 ratio, while the 780M has no recorded FP16 support. Pixel rate is 85.68 GPixel/s versus 25.50 GPixel/s, and texture rate is 157.1 GTexel/s versus 102.0 GTexel/s.

Specification Differences

The two cards differ in nearly every specification. The 1660 SUPER is a dual-slot desktop card with a 1x 8-pin power connector and a suggested PSU of 300 W. The 780M is an MXM module with no power connectors, designed for portable devices. The 1660 SUPER has a length of 229 mm, a height of 111 mm, and a width of 35 mm. The 780M has no recorded dimensions.

The 1660 SUPER has a TDP of 125 W, slightly higher than the 780M's 122 W, but the 1660 SUPER delivers far more performance per watt. The 1660 SUPER connects via PCIe 3.0 x16, while the 780M uses MXM-B (3.0). Display outputs also differ: the 1660 SUPER has 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a, while the 780M's outputs are listed as portable device dependent.

The 1660 SUPER was released on 2019-10-28 and has a launch MSRP of 229 USD. The 780M was released on 2013-05-10 and has no recorded launch MSRP. Both are end-of-life products. The 1660 SUPER's predecessor is the GeForce 10 series and its successor is the GeForce 20 series. The 780M's predecessor is the GeForce 600M series and its successor is the GeForce 800M series.

Memory configuration is another key difference. The 1660 SUPER has 6 GB of GDDR6 with a 192 bit bus and 336.0 GB/s bandwidth. The 780M has 4 GB of GDDR5 with a 256 bit bus and 160.0 GB/s bandwidth. The 1660 SUPER has more memory, newer memory technology, and more than double the bandwidth despite the narrower bus.

API support differs as well. The 1660 SUPER supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The 780M supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. The newer API versions on the 1660 SUPER give it better compatibility with modern games and applications.

FAQ

Q: Which card is faster in Geekbench OpenCL?

A: The GTX 1660 SUPER scores 52490, which is 311.1% higher than the GTX 780M's 12769.

Q: How much faster is the GTX 1660 SUPER in Vulkan?

A: The 1660 SUPER scores 57102 in Geekbench Vulkan, a 349.8% improvement over the 780M's 12696.

Q: What are the memory specifications for each card?

A: The 1660 SUPER has 6 GB of GDDR6 with a 192 bit bus and 336.0 GB/s bandwidth. The 780M has 4 GB of GDDR5 with a 256 bit bus and 160.0 GB/s bandwidth.

Q: Which card has a higher transistor density?

A: The 1660 SUPER has 23.2M transistors per mm², while the 780M has 12.0M per mm². The 1660 SUPER uses a 12 nm process, and the 780M uses 28 nm.

Q: What is the average benchmark score for each card?

A: The 1660 SUPER has an average score of 12986, placing it at the 53rd percentile. The 780M averages 11261, which is the 50th percentile.

Q: Do both cards support the same API versions?

A: No. The 1660 SUPER supports DirectX 12 (12_1) and Vulkan 1.4. The 780M supports DirectX 12 (11_0) and Vulkan 1.2.175.

The Verdict

The data is unambiguous. The GTX 1660 SUPER is dramatically faster than the GTX 780M in every recorded benchmark. The 311.1% lead in OpenCL and 349.8% lead in Vulkan are not incremental improvements; they represent a generational leap in performance. The 1660 SUPER's average score of 12986 versus 11261 for the 780M confirms that this is not a close comparison.

Anyone considering a laptop with a GTX 780M should understand that it is an end-of-life product from 2013 with no modern API support beyond Vulkan 1.2.175. Its 2.448 TFLOPS of FP32 performance and 160.0 GB/s of memory bandwidth are simply not competitive with the 1660 SUPER's 5.027 TFLOPS and 336.0 GB/s. The 780M has more shading units and TMUs, but the 1660 SUPER's higher clocks and newer architecture make those numbers irrelevant.

The GTX 1660 SUPER is the clear choice for anyone building a system today. It has newer memory, more of it, faster clocks, better API support, and a much higher average benchmark score. The 780M was a capable mobile part in its time, but the database shows that time has passed. The 1660 SUPER is the card to pick for modern workloads, and the 780M should only be considered for legacy systems where its MXM form factor is required.