Intel UHD Graphics P750 vs NVIDIA GeForce GTX 1660 Ti Comparison

Head-to-Head Benchmarks

The only common benchmark recorded for both the NVIDIA GeForce GTX 1660 Ti and the Intel UHD Graphics P750 is Geekbench OpenCL, and the result is decisively one-sided. The NVIDIA part scores 51,029 points, while the Intel integrated solution manages 6,554 points. This translates to a delta of 678.6%, meaning the GeForce GTX 1660 Ti delivers over seven times the raw compute performance in this specific workload. The data shows a complete sweep: the GTX 1660 Ti wins the sole head-to-head test, and the Intel UHD Graphics P750 records zero wins in any comparative benchmark.

When placed against the broader database, these two parts occupy surprisingly similar percentile territory despite the massive score gap. The GTX 1660 Ti sits at the 41st percentile among all GPUs, while the UHD Graphics P750 lands at the 38th percentile. The average benchmark score for the NVIDIA card is 7,723, based on ten different tests, whereas the Intel part averages 6,554 from a single Geekbench OpenCL result. This suggests that while the GTX 1660 Ti dominates in raw OpenCL compute, the Intel chip is not as far behind in the overall distribution as the 678.6% delta might imply. The reason lies in the nature of the tests: the GTX 1660 Ti's other benchmarks, such as Passmark G3D at 12,871 or 3DMark Steel Nomad at 1,061, pull its average down, while the Intel part's lone score defines its entire profile.

The nearest rival data further contextualizes each card. The GTX 1660 Ti is bracketed by AMD Radeon 540 (average score 7,673, delta 0.7%), AMD Radeon Pro WX 3100 (7,580, delta 1.9%), AMD Radeon R7 250 (7,557, delta 2.2%), and Intel Arc A310 (7,550, delta 2.3%). These are all within a narrow band, meaning the GTX 1660 Ti's average score is merely 0.7% ahead of the Radeon 540 and 2.3% ahead of the Arc A310. For the Intel UHD Graphics P750, the nearest rivals are AMD Radeon HD 7730M (6,581, delta -0.4%), NVIDIA GeForce GTX 670M (6,513, delta 0.6%), AMD Radeon R7 M460 (6,612, delta -0.9%), and NVIDIA GeForce GT 555M (6,493, delta 0.9%). The Intel chip is effectively neck-and-neck with these older discrete mobile parts, trailing the R7 M460 by 0.9% and leading the GTX 670M by 0.6%.

The benchmark results indicate that the GTX 1660 Ti is not just faster than the UHD Graphics P750; it is in a completely different performance class for compute-heavy tasks. However, the percentile data reveals that both are mid-to-low tier in the overall GPU landscape, with the GTX 1660 Ti being slightly above the median mark and the Intel part just below it.

Architecture Differences

The two GPUs come from fundamentally different design philosophies. The NVIDIA GeForce GTX 1660 Ti is built on the Turing architecture, using the TU116 chip fabricated on TSMC's 12 nm process. The die measures 284 mm² and contains 6,600 million transistors, yielding a transistor density of 23.2 million per square millimeter. The Intel UHD Graphics P750, by contrast, is based on Generation 12.1 architecture, specifically the Rocket Lake chip, manufactured on Intel's 14 nm+++ process. Intel does not disclose transistor count, die size, or density for this part, which is typical for an integrated graphics processor embedded within a larger CPU die.

The GTX 1660 Ti is a discrete, dual-slot card with a 229 mm length, 111 mm height, and 35 mm width, requiring a 1x 8-pin power connector and a 300 W suggested power supply. Its thermal design power is 120 W. The UHD Graphics P750 is an IGP (integrated graphics processor) with no slot width, no power connectors, no suggested PSU, and a 15 W TDP. It connects to the rest of the system via a Ring Bus, whereas the GTX 1660 Ti uses PCIe 3.0 x16. Display outputs on the NVIDIA card include 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a, while the Intel part's outputs are motherboard dependent.

Memory architecture is another stark differentiator. The GTX 1660 Ti has 6 GB of dedicated GDDR6 memory on a 192-bit bus, delivering 288.0 GB/s of bandwidth. The UHD Graphics P750 uses System Shared memory, meaning it has no dedicated VRAM; the memory type, bus width, and bandwidth are all system dependent. The clock speeds also diverge: the NVIDIA card has a base clock of 1500 MHz and a boost clock of 1770 MHz, with memory running at 1500 MHz (12 Gbps effective). The Intel part has a much lower base clock of 350 MHz, boosting to 1300 MHz, with no separate memory clock since it shares system memory.

The core configurations are vastly different. The GTX 1660 Ti has 1,536 shading units, 96 texture mapping units (TMUs), and 48 raster operation units (ROPs). The UHD Graphics P750 has only 256 shading units, 64 TMUs, and 32 ROPs. Neither card has dedicated ray tracing cores or tensor cores. The resulting pixel and texture rates reflect these differences: the GTX 1660 Ti achieves 84.96 GPixel/s and 169.9 GTexel/s, while the Intel part manages 41.60 GPixel/s and 83.20 GTexel/s. Floating-point performance follows the same pattern, with the NVIDIA card delivering 5.437 TFLOPS FP32 and 10.87 TFLOPS FP16 (2:1 ratio), versus 665.6 GFLOPS FP32 and 1,331.2 GFLOPS FP16 for the Intel chip.

Both support DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4, so API compatibility is not a differentiator. The GTX 1660 Ti was released on February 21, 2019, with a launch MSRP of 279 USD, and is now end-of-life. The UHD Graphics P750 has no recorded release date or MSRP, and it is also end-of-life.

The Verdict

The data is unambiguous: the NVIDIA GeForce GTX 1660 Ti outperforms the Intel UHD Graphics P750 by a massive margin in the only directly comparable benchmark. The 678.6% delta in Geekbench OpenCL is not a marginal improvement; it is a generational leap. The GTX 1660 Ti's 51,029 score versus the Intel part's 6,554 places them in different leagues for compute workloads. However, the percentile rankings tell a subtler story. The GTX 1660 Ti is at the 41st percentile, while the UHD Graphics P750 is at the 38th. This means that while the NVIDIA card is absolutely faster, both are below the median GPU in the database. The Intel part is not catastrophically bad; it is simply an integrated solution designed for basic tasks, whereas the GTX 1660 Ti is a discrete card aimed at 1080p gaming and content creation.

Who should pick which? The GTX 1660 Ti is the obvious choice for anyone needing dedicated graphics performance, as evidenced by its 1,536 shading units, 6 GB of GDDR6, and 288 GB/s bandwidth. It can handle modern gaming and GPU-accelerated workloads. The UHD Graphics P750, with its 256 shading units, shared system memory, and 15 W TDP, is suitable only for systems where power consumption is critical and graphics demands are minimal, such as office productivity or basic media playback. The data does not support any scenario where the Intel part wins a performance comparison; it is strictly a power-efficient fallback. The GTX 1660 Ti's nearest rivals (AMD Radeon 540, Radeon Pro WX 3100, Radeon R7 250, Intel Arc A310) are all within 2.3% of its average score, indicating it is a mid-tier card, not a high-end one. The Intel part's nearest rivals (AMD Radeon HD 7730M, GTX 670M, R7 M460, GT 555M) are all older mobile GPUs, further cementing its position as entry-level.

Specification Differences

The following fields differ between the two parts:

• Architecture: Turing (NVIDIA) vs Generation 12.1 (Intel)
• Chip: TU116 (NVIDIA) vs Rocket Lake (Intel)
• Process Node: 12 nm (NVIDIA, TSMC) vs 14 nm+++ (Intel)
• Transistors: 6,600 million (NVIDIA) vs not disclosed (Intel)
• Die Size: 284 mm² (NVIDIA) vs not disclosed (Intel)
• Transistor Density: 23.2M / mm² (NVIDIA) vs not disclosed (Intel)
• Base Clock: 1500 MHz (NVIDIA) vs 350 MHz (Intel)
• Boost Clock: 1770 MHz (NVIDIA) vs 1300 MHz (Intel)
• Memory Clock: 1500 MHz, 12 Gbps effective (NVIDIA) vs System Shared (Intel)
• Memory Size: 6 GB GDDR6 (NVIDIA) vs System Shared (Intel)
• Memory Bus Width: 192 bit (NVIDIA) vs System Shared (Intel)
• Memory Bandwidth: 288.0 GB/s (NVIDIA) vs System Dependent (Intel)
• Shading Units: 1,536 (NVIDIA) vs 256 (Intel)
• TMUs: 96 (NVIDIA) vs 64 (Intel)
• ROPs: 48 (NVIDIA) vs 32 (Intel)
• Pixel Rate: 84.96 GPixel/s (NVIDIA) vs 41.60 GPixel/s (Intel)
• Texture Rate: 169.9 GTexel/s (NVIDIA) vs 83.20 GTexel/s (Intel)
• FP32: 5.437 TFLOPS (NVIDIA) vs 665.6 GFLOPS (Intel)
• FP16: 10.87 TFLOPS (NVIDIA) vs 1,331.2 GFLOPS (Intel)
• TDP: 120 W (NVIDIA) vs 15 W (Intel)
• Slot Width: Dual-slot (NVIDIA) vs IGP (Intel)
• Power Connectors: 1x 8-pin (NVIDIA) vs none (Intel)
• Suggested PSU: 300 W (NVIDIA) vs none (Intel)
• Bus Interface: PCIe 3.0 x16 (NVIDIA) vs Ring Bus (Intel)
• Display Outputs: 1x DVI, 1x HDMI 2.0, 1x DisplayPort 1.4a (NVIDIA) vs Motherboard Dependent (Intel)
• Dimensions: 229 mm x 111 mm x 35 mm (NVIDIA) vs not disclosed (Intel)
• Release Date: 2019-02-21 (NVIDIA) vs not disclosed (Intel)
• Launch MSRP: 279 USD (NVIDIA) vs none (Intel)
• Predecessor: GeForce 10 (NVIDIA) vs none (Intel)
• Successor: GeForce 20 (NVIDIA) vs none (Intel)

FAQ

Q: How much faster is the NVIDIA GeForce GTX 1660 Ti than the Intel UHD Graphics P750 in Geekbench OpenCL?

A: The GTX 1660 Ti scores 51,029 points versus 6,554 for the Intel part, a delta of 678.6% in favor of the NVIDIA card.

Q: Which GPU has a higher percentile ranking among all GPUs?

A: The GTX 1660 Ti is at the 41st percentile, while the UHD Graphics P750 is at the 38th percentile, so the NVIDIA card ranks slightly higher.

Q: What are the nearest rivals to each GPU based on average benchmark score?

A: For the GTX 1660 Ti, the nearest rivals are AMD Radeon 540 (7,673, delta 0.7%), AMD Radeon Pro WX 3100 (7,580, delta 1.9%), AMD Radeon R7 250 (7,557, delta 2.2%), and Intel Arc A310 (7,550, delta 2.3%). For the UHD Graphics P750, the nearest rivals are AMD Radeon R7 M460 (6,612, delta -0.9%), AMD Radeon HD 7730M (6,581, delta -0.4%), NVIDIA GeForce GTX 670M (6,513, delta 0.6%), and NVIDIA GeForce GT 555M (6,493, delta 0.9%).

Q: How much memory does each GPU have?

A: The GTX 1660 Ti has 6 GB of GDDR6 on a 192-bit bus with 288.0 GB/s bandwidth. The UHD Graphics P750 uses System Shared memory, with type, bus width, and bandwidth all system dependent.

Q: What is the TDP difference between the two?

A: The GTX 1660 Ti has a TDP of 120 W, while the UHD Graphics P750 has a TDP of 15 W, making the Intel part much more power-efficient.

Q: Which GPU has more shading units?

A: The GTX 1660 Ti has 1,536 shading units, whereas the UHD Graphics P750 has 256 shading units, a 6x difference.

Where Each One Wins

The NVIDIA GeForce GTX 1660 Ti wins in every measurable performance category. In the single head-to-head benchmark, it wins outright with a 678.6% lead. Its shading unit count (1,536 vs 256), TMU count (96 vs 64), and ROP count (48 vs 32) give it clear advantages in pixel and texture processing. The 6 GB of dedicated GDDR6 memory with 288.0 GB/s bandwidth allows it to handle large textures and high resolutions, while the Intel part's system-shared memory is a bottleneck. The GTX 1660 Ti's FP32 performance of 5.437 TFLOPS is over eight times the Intel part's 665.6 GFLOPS, making it suitable for compute-heavy tasks like 3D rendering, video editing, and gaming.

The Intel UHD Graphics P750 has no benchmark wins against the GTX 1660 Ti. Its only advantage is power consumption: a 15 W TDP versus 120 W, and it requires no additional power connectors or a suggested PSU. It is an IGP with no physical dimensions, making it suitable for compact systems where a discrete card cannot fit. Its base clock of 350 MHz and boost of 1300 MHz are far lower, but they are sufficient for basic desktop tasks. The Intel part's nearest rivals are all older discrete mobile GPUs, indicating it performs at the level of a low-end laptop graphics chip. In scenarios where the system must run on minimal power and graphics demands are limited to 2D applications, the UHD Graphics P750 is the only viable choice. But for any workload that stresses the GPU, the GTX 1660 Ti is the clear winner, and the data does not suggest any scenario where the Intel part provides a better user experience for gaming or GPU-accelerated compute.