Intel UHD Graphics P750 vs NVIDIA GeForce GTX 765M Comparison

Head-to-Head Benchmarks

The database records a single direct comparison between these two mobile graphics solutions: the Geekbench OpenCL test. In that test, the NVIDIA GeForce GTX 765M scores 7,176 points, while the Intel UHD Graphics P750 scores 6,554 points. This gives the NVIDIA part an 8.7% lead in raw compute throughput. The delta of -8.7% for the Intel part means it trails by that margin.

This result places the GTX 765M clearly ahead in the one metric where both have recorded data. The Intel UHD Graphics P750’s score of 6,554 is close to several rivals in its own percentile neighborhood. It sits within 0.9% of the NVIDIA GeForce GT 555M (6,493) and 0.6% of the NVIDIA GeForce GTX 670M (6,513). It is also only 0.4% behind the AMD Radeon HD 7730M (6,581) and 0.9% behind the AMD Radeon R7 M460 (6,612). The P750 is not far off the pace of these older discrete parts, despite being an integrated processor graphics solution.

The GTX 765M’s OpenCL score of 7,176 places it in a different competitive bracket. Its nearest rivals in the database include the NVIDIA GeForce MX130 (5,508, a 0.1% difference), the AMD Radeon R7 M440 (5,483, a 0.3% difference), the NVIDIA Quadro M4000 (5,467, a 0.6% difference), and the AMD FirePro M4000 (5,537, a 0.7% difference). The GTX 765M is roughly 30% faster than these nearby entries in OpenCL, which shows a significant gap between it and the lower-tier mobile parts that cluster around its average score.

The GTX 765M also has additional benchmark records that the Intel part lacks. It scores 2,612 in Geekbench Metal and 6,714 in Geekbench Vulkan. These results cannot be compared directly to the P750, but they do indicate that the NVIDIA GPU has functional drivers and performance levels for both Apple’s Metal API and the Vulkan API. The Intel part has no recorded Metal or Vulkan scores in the database.

Where Each One Wins

The NVIDIA GeForce GTX 765M wins the only head-to-head benchmark, the OpenCL test, by 8.7%. This is the definitive win for the discrete mobile GPU. It also holds a substantial advantage in raw shading resources: 768 shading units versus 256 for the Intel part. That threefold difference in shader count aligns with the performance lead seen in OpenCL, though the final score gap is smaller than the hardware disparity might suggest.

The Intel UHD Graphics P750 does not win any recorded benchmark against the GTX 765M. Its win condition is not in raw compute but in efficiency and integration. The P750 is a 15 W integrated processor graphics solution, while the GTX 765M is a 75 W MXM module. The Intel part operates at a base clock of 350 MHz with a boost of 1,300 MHz; the NVIDIA part runs at 797 MHz base and 863 MHz boost. The Intel boost clock is 437 MHz higher than the NVIDIA boost, which helps close the gap despite the shader disadvantage.

The P750 also has a higher pixel rate at 41.60 GPixel/s versus 13.81 GPixel/s for the GTX 765M. This is a 3x advantage in pixel throughput. Its texture rate of 83.20 GTexel/s also exceeds the GTX 765M’s 55.23 GTexel/s by roughly 50%. These figures suggest that while the NVIDIA GPU has more compute shaders, the Intel part has superior fill rate capabilities per clock. In practice, this means the P750 may handle certain rasterization-heavy workloads more efficiently, but the GTX 765M’s higher overall compute score indicates stronger sustained performance in general-purpose compute tasks.

Architecture Differences

The two GPUs come from fundamentally different design philosophies. The Intel UHD Graphics P750 is built on Intel’s Generation 12.1 architecture, using the Rocket Lake chip. It is manufactured on Intel’s 14 nm+++ process node at Intel’s own foundry. The NVIDIA GeForce GTX 765M uses the Kepler architecture with the GK106 chip, manufactured by TSMC on a 28 nm process.

The process node difference is significant: 14 nm+++ versus 28 nm. The Intel part uses a more advanced manufacturing process, which contributes to its lower power draw of 15 W compared to 75 W for the NVIDIA part. The Intel foundry produces the P750, while TSMC produces the GK106.

The NVIDIA chip has a transparent transistor count and die size: 2,540 million transistors on a 221 mm² die, giving a density of 11.5 million transistors per square millimeter. The Intel part does not have recorded transistor count, die size, or density figures in the database.

Clock behavior also differs. The Intel P750 has a base clock of 350 MHz and a boost of 1,300 MHz, a 950 MHz range. The NVIDIA GTX 765M has a base of 797 MHz and boost of 863 MHz, a much narrower 66 MHz range. The Intel part’s boost clock is 437 MHz higher than the NVIDIA boost clock. Memory clocks are not directly comparable: the P750 uses system shared memory, while the GTX 765M has dedicated GDDR5 at 1,002 MHz with 4 Gbps effective speed.

The memory subsystem is one of the largest architectural splits. The P750 has system shared memory with a system dependent bandwidth. The GTX 765M has 2 GB of GDDR5 on a 128-bit bus with 64.13 GB/s bandwidth. The NVIDIA part’s dedicated memory provides predictable bandwidth for gaming workloads, while the Intel part depends entirely on the host system’s memory configuration.

Shader resources differ sharply: 256 shading units for Intel versus 768 for NVIDIA. Texture mapping units are equal at 64 each. Raster operation units favor Intel at 32 versus 16. The Intel part’s higher ROP count explains its pixel rate advantage. FP32 compute is 665.6 GFLOPS for Intel versus 1,325.6 GFLOPS for NVIDIA, a 2x advantage for the discrete part. The Intel part also lists FP16 at 1,331.2 GFLOPS with a 2:1 ratio, while the NVIDIA part has no recorded FP16 capability.

FAQ

Q: Which GPU has the higher OpenCL benchmark score?

A: The NVIDIA GeForce GTX 765M scores 7,176 in Geekbench OpenCL, which is 8.7% higher than the Intel UHD Graphics P750’s 6,554.

Q: Does the Intel UHD Graphics P750 have any fill rate advantages?

A: Yes. The P750 has a pixel rate of 41.60 GPixel/s versus 13.81 GPixel/s for the GTX 765M, and a texture rate of 83.20 GTexel/s versus 55.23 GTexel/s.

Q: What is the power consumption difference?

A: The Intel P750 has a TDP of 15 W, while the NVIDIA GTX 765M has a TDP of 75 W. The Intel part consumes 60 W less power.

Q: How much memory does each GPU have?

A: The Intel P750 uses system shared memory with system dependent bandwidth. The NVIDIA GTX 765M has 2 GB of dedicated GDDR5 memory on a 128-bit bus with 64.13 GB/s bandwidth.

Q: Which GPU has more shading units?

A: The NVIDIA GTX 765M has 768 shading units, three times the 256 shading units in the Intel P750.

Q: What API support differences exist?

A: The Intel P750 supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The NVIDIA GTX 765M supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175.

Specification Differences

| Specification | Intel UHD Graphics P750 | NVIDIA GeForce GTX 765M |

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

| Architecture | Generation 12.1 | Kepler |

| Chip | Rocket Lake | GK106 |

| Process Node | 14 nm+++ | 28 nm |

| Foundry | Intel | TSMC |

| Transistors | Not recorded | 2,540 million |

| Die Size | Not recorded | 221 mm² |

| Transistor Density | Not recorded | 11.5M / mm² |

| Base Clock | 350 MHz | 797 MHz |

| Boost Clock | 1,300 MHz | 863 MHz |

| Memory Size | System Shared | 2 GB |

| Memory Type | System Shared | GDDR5 |

| Memory Bus | System Shared | 128 bit |

| Memory Bandwidth | System Dependent | 64.13 GB/s |

| Shading Units | 256 | 768 |

| TMUs | 64 | 64 |

| ROPs | 32 | 16 |

| Pixel Rate | 41.60 GPixel/s | 13.81 GPixel/s |

| Texture Rate | 83.20 GTexel/s | 55.23 GTexel/s |

| FP32 | 665.6 GFLOPS | 1,325.6 GFLOPS |

| FP16 | 1,331.2 GFLOPS (2:1) | Not recorded |

| TDP | 15 W | 75 W |

| Slot Width | IGP | MXM Module |

| Bus Interface | Ring Bus | MXM-B (3.0) |

| DirectX | 12 (12_1) | 12 (11_0) |

| Vulkan | 1.4 | 1.2.175 |

| OpenCL Score | 6,554 | 7,176 |

The Verdict

The data points to a clear performance winner in the NVIDIA GeForce GTX 765M. Its 8.7% lead in OpenCL, combined with 2x the FP32 compute (1,325.6 GFLOPS versus 665.6 GFLOPS) and 3x the shading units (768 versus 256), makes it the stronger choice for compute-heavy tasks. The dedicated 2 GB GDDR5 memory with 64.13 GB/s bandwidth also provides a stable memory pipeline that the P750 cannot match with system shared memory.

The Intel UHD Graphics P750 is the appropriate selection when power efficiency matters more than raw performance. Its 15 W TDP is one-fifth of the GTX 765M’s 75 W. The P750 also has superior pixel rate (41.60 GPixel/s versus 13.81 GPixel/s) and texture rate (83.20 GTexel/s versus 55.23 GTexel/s), which suggests it can handle fill-rate-bound workloads with proportionally less power. Its higher boost clock of 1,300 MHz versus 863 MHz helps compensate for fewer shaders in some scenarios.

For a portable device where battery life and thermal output are primary constraints, the Intel integrated solution is the logical fit. For a laptop that needs consistent gaming or compute performance and has the power budget to support a discrete MXM module, the NVIDIA GTX 765M is the better choice. The recorded benchmarks show a single OpenCL win for NVIDIA, and the specification data reinforces that outcome for general compute, while the Intel part wins on efficiency and fill rate.