NVIDIA GeForce GT 1010 vs NVIDIA GeForce GTX 1660 Ti Comparison

Head-to-Head Benchmarks

The recorded data includes a single direct comparison between these two cards. In the Geekbench OpenCL compute test, the NVIDIA GeForce GTX 1660 Ti scores 51,029 points against 6,698 for the NVIDIA GeForce GT 1010. That is a 661.9% advantage for the GTX 1660 Ti, a massive performance gap that defines the entire relationship between these products.

The GTX 1660 Ti has a much wider benchmark footprint in the database. It records scores across ten separate tests, including PassMark DirectX 9, 10, 11, and 12, plus compute workloads. Its strongest single result is the Geekbench OpenCL score, and its PassMark G3D score sits at 12,871. The GT 1010 has only one recorded benchmark result, the Geekbench OpenCL score of 6,698, which stands as its average.

Looking at the average benchmark score, the GTX 1660 Ti lands at 7,723, while the GT 1010 sits at 6,698. That difference, about 15%, is far smaller than the OpenCL gap because the GTX's average includes many low-level DirectX and compute tests where it scores lower in absolute terms. For example, the GTX 1660 Ti scores only 51 in PassMark DirectX 12 and 66 in DirectX 10, which drags down its mean. The GT 1010 has no such low scores pulling its average down, since only one result exists.

The percentile data places the GTX 1660 Ti in the 41st percentile among all GPUs, while the GT 1010 sits at the 38th percentile. These are close positions, but they mask the huge compute delta in the head-to-head test. The nearest rivals for the GTX 1660 Ti are all AMD or Intel parts: the Radeon 540 sits 0.7% behind, the Radeon Pro WX 3100 trails by 1.9%, the Radeon R7 250 by 2.2%, and the Intel Arc A310 by 2.3%. The GT 1010's nearest rivals are mobile-oriented AMD parts: the Radeon R7 M370 is 1% ahead, the Radeon R7 M460 trails by 1.3%, the Radeon HD 7730M trails by 1.8%, and the FirePro M5100 is 1.9% ahead.

Architecture Differences

The two cards come from different architectures and different foundries. The GTX 1660 Ti uses the TU116 chip built on a 12 nanometer process at TSMC, while the GT 1010 uses the GP108 chip built on a 14 nanometer process at Samsung. The transistor counts reflect the size gap: the TU116 holds 6,600 million transistors on a 284 mm² die, while the GP108 holds 1,800 million on a 74 mm² die. The transistor density is close, 23.2M per mm² for the GTX 1660 Ti versus 24.3M per mm² for the GT 1010, but the total compute resources differ dramatically.

The GTX 1660 Ti has 1,536 shading units, 96 texture mapping units, and 48 raster output units. The GT 1010 has 256 shading units, 16 TMUs, and 8 ROPs. That is 6 times the shading units, 6 times the TMUs, and 6 times the ROPs for the GTX 1660 Ti. Neither card has ray tracing cores or tensor cores, so the feature gap is purely about classic rasterization throughput.

The GTX 1660 Ti reaches a base clock of 1500 MHz and a boost clock of 1770 MHz, while the GT 1010 runs at 1228 MHz base and 1468 MHz boost. Pixel rate is 84.96 GPixel/s for the GTX 1660 Ti versus 11.74 GPixel/s for the GT 1010. Texture rate is 169.9 GTexel/s versus 23.49 GTexel/s. In FP32 compute, the GTX 1660 Ti delivers 5.437 TFLOPS, while the GT 1010 manages 751.6 GFLOPS. The GTX 1660 Ti also offers FP16 at 10.87 TFLOPS with a 2:1 ratio, while the GT 1010 has no recorded FP16 capability.

Memory technology differs as well. The GTX 1660 Ti uses 6 GB of GDDR6 on a 192-bit bus with 288.0 GB/s of bandwidth. The GT 1010 uses 2 GB of GDDR5 on a 64-bit bus with 48.06 GB/s. Memory speed is 12 Gbps effective for the GTX 1660 Ti versus 6 Gbps for the GT 1010.

FAQ

Q: Which card wins in compute workloads?

A: The GTX 1660 Ti dominates. Its Geekbench OpenCL score is 51,029 versus 6,698 for the GT 1010, a 661.9% delta. The GT 1010 has no recorded compute benchmark other than OpenCL.

Q: Do both cards support the same APIs?

A: Yes. Both report DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. This means both can run modern game titles, but the GTX 1660 Ti has the raw resources to do so at usable settings.

Q: Which card has more memory bandwidth?

A: The GTX 1660 Ti has 288.0 GB/s, compared to 48.06 GB/s for the GT 1010. That is a 6x difference in bandwidth, which directly affects resolution and texture-heavy workloads.

Q: How many display outputs does each card have?

A: The GTX 1660 Ti has 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a. The GT 1010 has 1x DVI and 1x mini-HDMI 2.0. The GTX 1660 Ti supports a DisplayPort output which the GT 1010 lacks.

Q: What is the power draw difference?

A: The GTX 1660 Ti has a TDP of 120 W and needs a 1x 8-pin power connector, with a suggested PSU of 300 W. The GT 1010 has a TDP of 30 W, no external power connector, and a suggested PSU of 200 W.

Q: Which card has a higher transistor density?

A: The GT 1010 has a slightly higher density at 24.3M / mm² versus 23.2M / mm² for the GTX 1660 Ti, but the GTX has nearly 4 times the total transistors.

Specification Differences

| Specification | GTX 1660 Ti | GT 1010 |

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

| Architecture | Turing | Pascal |

| Process Node | 12 nm | 14 nm |

| Foundry | TSMC | Samsung |

| Transistors | 6,600 million | 1,800 million |

| Die Size | 284 mm² | 74 mm² |

| Base Clock | 1500 MHz | 1228 MHz |

| Boost Clock | 1770 MHz | 1468 MHz |

| Effective Memory Speed | 12 Gbps | 6 Gbps |

| Memory Size | 6 GB | 2 GB |

| Memory Type | GDDR6 | GDDR5 |

| Memory Bus Width | 192 bit | 64 bit |

| Memory Bandwidth | 288.0 GB/s | 48.06 GB/s |

| Shading Units | 1536 | 256 |

| TMUs | 96 | 16 |

| ROPs | 48 | 8 |

| Pixel Rate | 84.96 GPixel/s | 11.74 GPixel/s |

| Texture Rate | 169.9 GTexel/s | 23.49 GTexel/s |

| FP32 Compute | 5.437 TFLOPS | 751.6 GFLOPS |

| FP16 Compute | 10.87 TFLOPS (2:1) | None |

| TDP | 120 W | 30 W |

| Slot Width | Dual-slot | Single-slot |

| Power Connectors | 1x 8-pin | None |

| Suggested PSU | 300 W | 200 W |

| Bus Interface | PCIe 3.0 x16 | PCIe 3.0 x4 |

| Display Outputs | 1x DVI, 1x HDMI 2.0, 1x DP 1.4a | 1x DVI, 1x mini-HDMI 2.0 |

| Dimensions (Length) | 229 mm / 9 inches | 147 mm / 5.8 inches |

| Release Date | 2019-02-21 | 2021-01-12 |

| Predecessor | GeForce 10 | GeForce 900 |

| Successor | GeForce 20 | GeForce 20 |

Where Each One Wins

The GTX 1660 Ti wins on every measurable performance axis. In compute, it is 661.9% ahead in OpenCL. In rasterization, it has 6 times the shading units, TMUs, and ROPs. It has 3 times the memory capacity, 6 times the memory bus width, and 6 times the memory bandwidth. Its pixel rate is 84.96 GPixel/s versus 11.74 GPixel/s, and its texture rate is 169.9 GTexel/s versus 23.49 GTexel/s.

The GT 1010 wins in efficiency and physical size. It consumes 30 W versus 120 W, requires no external power connector, and has a suggested PSU of 200 W versus 300 W. It is a single-slot card at 147 mm length, while the GTX 1660 Ti is a dual-slot card at 229 mm. The GT 1010 also has a slightly higher transistor density, 24.3M / mm² versus 23.2M / mm², which is a subtle advantage in technical layout, not real-world performance.

The GT 1010 also wins on its nearest rival comparisons, where it competes with mobile AMD parts. Its closest competitor is the AMD Radeon R7 M370, which is only 1% faster. The GTX 1660 Ti, by contrast, faces desktop competition from the Radeon 540, which is only 0.7% faster. This shows that the GT 1010 sits in the entry-level performance class, while the GTX 1660 Ti sits in the mid-range.

The Verdict

The recorded data makes this a one-sided comparison. The GTX 1660 Ti is overwhelmingly faster in every compute and rasterization metric, and the only benchmark where both have results shows a 661.9% lead for the GTX 1660 Ti. If the task is any kind of 3D graphics, gaming, or general GPU compute, the GTX 1660 Ti is the only rational choice from the data.

The GT 1010's advantages are strictly physical: lower power draw (30 W versus 120 W), no external power connector, single-slot size, and a shorter length of 147 mm versus 229 mm. These are meaningful for a low-profile system where space and cooling are extremely tight. For a basic display output at the desktop, the GT 1010 is sufficient, and its lack of a power connector makes it easy to install. But the data shows no scenario where the GT 1010 wins a performance test.

The decision comes down to intent. The GTX 1660 Ti is for anyone who needs actual rendering capability, be it for light gaming, older titles, or compute tasks. The GT 1010 is for a system that only needs a video output and minimal acceleration. The benchmark database places the GTX 1660 Ti at the 42nd percentile and the GT 1010 at the 38th percentile, but that gap understates the real difference in workload capability. The GTX 1660 Ti is the only card here that can handle modern 3D workloads with any reasonable expectation of playability. The GT 1010 is a last-resort or low-power solution.

For any builder who has the power budget and physical space, the GTX 1660 Ti is the clear pick. For a rigid system that cannot supply a PCIe power cable or fit a dual-slot cooler, the GT 1010 is the only option that fits, but it will not deliver a gaming experience. The data does not support any other conclusion.