Intel UHD Graphics P750 vs NVIDIA GeForce GTX 670MX Comparison

The Verdict

The benchmark database shows a clear, if narrow, overall winner in this matchup. The Intel UHD Graphics P750 takes the single recorded head-to-head benchmark, Geekbench OpenCL, with a score of 6554 against the NVIDIA GeForce GTX 670MX's 6125, a 7% advantage. This places the Intel part at the 38th percentile of all GPUs, while the NVIDIA part sits at the 33rd percentile, confirming its lower standing in the overall performance distribution.

For a user choosing between these two end-of-life mobile graphics solutions, the data points to the Intel UHD Graphics P750 as the stronger compute performer in the measured workload. Its average benchmark score of 6554 is higher than the GTX 670MX's average of 5721, a substantial gap that reflects the NVIDIA part's weaker Vulkan result (5316) dragging down its average. The Intel part also benefits from a much lower 15 W TDP compared to the NVIDIA part's 75 W, making it the more power-efficient choice on paper, though the NVIDIA part is a discrete GPU with dedicated memory, which changes the system context.

However, the GTX 670MX is not without its own arguments. It offers 3 GB of dedicated GDDR5 memory on a 192-bit bus with 67.20 GB/s of bandwidth, which is a fundamentally different memory subsystem than the Intel part's system-shared memory. The NVIDIA part also has significantly more shading units (960 versus 256) and texture mapping units (80 versus 64), which suggests it may have strengths in workloads that leverage those resources. The recorded data, however, shows the Intel part winning the only benchmark where both have results. Users prioritizing raw compute in the Geekbench OpenCL test, power efficiency, and a more modern API profile (DirectX 12_1, Vulkan 1.4) should favor the Intel UHD Graphics P750. Users who need dedicated VRAM and a more traditional discrete GPU form factor, or who are tied to the GeForce 600M ecosystem, may still consider the GTX 670MX, but the benchmark data does not favor it.

Architecture Differences

The two GPUs come from opposite ends of the design spectrum. The Intel UHD Graphics P750 is built on the Rocket Lake chip using Intel's Generation 12.1 architecture, fabricated on a 14 nm+++ process at Intel's own foundry. It is an integrated graphics processor (IGP) with a Ring Bus interface, meaning it shares system memory and its display outputs are dependent on the motherboard. The NVIDIA GeForce GTX 670MX, by contrast, is a discrete mobile GPU based on the GK104 chip, using NVIDIA's Kepler architecture, fabricated on a 28 nm process at TSMC. It uses a PCIe 3.0 x16 interface and has its own dedicated memory, with display outputs dependent on the portable device.

The transistor budgets tell a stark story. The GTX 670MX packs 3,540 million transistors into a 294 mm² die, with a transistor density of 12.0M / mm². The Intel part has no recorded transistor count or die size in the database, but its architecture is fundamentally different, integrating graphics into a processor package. The clock behavior also diverges: the Intel part has a base clock of 350 MHz and a boost clock of 1300 MHz, allowing it to ramp up under load. The NVIDIA part runs at a fixed 601 MHz for both base and boost, with its memory clocked at 700 MHz (2.8 Gbps effective).

The compute resources are heavily skewed toward the NVIDIA part in raw count. The GTX 670MX has 960 shading units, 80 TMUs, and 24 ROPs. The Intel UHD Graphics P750 has 256 shading units, 64 TMUs, and 32 ROPs. Despite having fewer shaders and TMUs, the Intel part achieves higher pixel and texture rates: 41.60 GPixel/s versus 12.02 GPixel/s, and 83.20 GTexel/s versus 48.08 GTexel/s. This is a striking result of the Intel part's much higher boost clock and its different execution architecture. In FP32 compute, the NVIDIA part leads with 1,153.9 GFLOPS versus 665.6 GFLOPS for the Intel part, but the Intel part offers FP16 at 1,331.2 GFLOPS (2:1), a capability the NVIDIA part does not list.

API support also differs meaningfully. The Intel part supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The NVIDIA part supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. The Intel part has a more modern feature level for DirectX and a newer Vulkan version. Both are marked as end-of-life, with the NVIDIA part having a release date of 2012-09-30 and a known predecessor (GeForce 500M) and successor (GeForce 700M), while the Intel part has no recorded release date or lineage.

FAQ

Q: Which GPU has the higher benchmark score in the recorded data?

A: The Intel UHD Graphics P750 scores 6554 in Geekbench OpenCL, which is 7% higher than the NVIDIA GeForce GTX 670MX's 6125 in the same test. The Intel part also has a higher average benchmark score of 6554 versus 5721 for the NVIDIA part.

Q: How do these GPUs compare to their nearest rivals in the database?

A: The Intel UHD Graphics P750 sits 0.4% behind the AMD Radeon HD 7730M (6581), 0.6% ahead of the NVIDIA GeForce GTX 670M (6513), 0.9% behind the AMD Radeon R7 M460 (6612), and 0.9% ahead of the NVIDIA GeForce GT 555M (6493). The NVIDIA GeForce GTX 670MX sits 0.2% ahead of the Intel Iris Pro Graphics P6300 (5712), 0.2% behind the NVIDIA GeForce GTX 550 Ti (5731), 0.5% ahead of the AMD Radeon HD 8790M (5691), and 2.1% ahead of the NVIDIA Quadro M500M (5604).

Q: What are the memory configurations of each GPU?

A: The Intel UHD Graphics P750 uses system-shared memory, with its size, type, and bus width all listed as system shared, and bandwidth as system dependent. The NVIDIA GeForce GTX 670MX has 3 GB of dedicated GDDR5 memory on a 192-bit bus, with 67.20 GB/s of bandwidth.

Q: Which GPU has better API support?

A: The Intel UHD Graphics P750 supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The NVIDIA GeForce GTX 670MX supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. The Intel part has a higher DirectX feature level and a newer Vulkan version.

Q: What is the power consumption difference between the two?

A: The Intel UHD Graphics P750 has a TDP of 15 W, while the NVIDIA GeForce GTX 670MX has a TDP of 75 W. The Intel part is rated for significantly lower power draw.

Q: What is the production status of these GPUs?

A: Both are marked as end-of-life. The NVIDIA GeForce GTX 670MX has a recorded release date of 2012-09-30, with the GeForce 500M as its predecessor and GeForce 700M as its successor. The Intel UHD Graphics P750 has no recorded release date, predecessor, or successor.

Specification Differences

The two GPUs differ in nearly every core specification. The Intel UHD Graphics P750 is fabricated on a 14 nm+++ process at Intel's foundry, while the NVIDIA GeForce GTX 670MX uses a 28 nm process at TSMC. The NVIDIA part has a recorded transistor count of 3,540 million and die size of 294 mm², with a transistor density of 12.0M / mm²; the Intel part has no recorded values for these fields. Clock speeds differ: the Intel part runs at 350 MHz base and 1300 MHz boost, while the NVIDIA part runs at 601 MHz for both base and boost. The NVIDIA memory clock is 700 MHz (2.8 Gbps effective), while the Intel memory clock is listed as system shared.

Compute resources show a major divergence. The Intel part has 256 shading units, 64 TMUs, and 32 ROPs, while the NVIDIA part has 960 shading units, 80 TMUs, and 24 ROPs. Pixel rate favors the Intel part at 41.60 GPixel/s versus 12.02 GPixel/s, and texture rate favors Intel at 83.20 GTexel/s versus 48.08 GTexel/s. FP32 compute favors NVIDIA at 1,153.9 GFLOPS versus 665.6 GFLOPS, but the Intel part offers FP16 at 1,331.2 GFLOPS (2:1), which the NVIDIA part does not list. The NVIDIA part has 3 GB of GDDR5 on a 192-bit bus with 67.20 GB/s bandwidth; the Intel part uses system-shared memory with system-dependent bandwidth.

Power and interface also differ. The Intel part has a 15 W TDP and a Ring Bus interface, while the NVIDIA part has a 75 W TDP and PCIe 3.0 x16. The Intel part is an IGP with motherboard-dependent display outputs; the NVIDIA part has portable-device-dependent outputs and no power connectors. API support: Intel has DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4; NVIDIA has DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. The NVIDIA part has a recorded release date of 2012-09-30, while the Intel part has none.

Head-to-Head Benchmarks

The database contains exactly one head-to-head benchmark between these two parts: Geekbench OpenCL. The Intel UHD Graphics P750 scores 6554, and the NVIDIA GeForce GTX 670MX scores 6125. The Intel part wins with a 7% delta. This result aligns with the overall percentile ranking, where the Intel part sits at the 38th percentile versus the NVIDIA part's 33rd percentile.

The Geekbench OpenCL result is the only direct comparison available, but it is telling. The Intel part's score of 6554 places it just 0.4% behind the AMD Radeon HD 7730M (6581) and 0.6% ahead of the NVIDIA GeForce GTX 670M (6513). The NVIDIA GeForce GTX 670MX's score of 6125 in the same test is noticeably lower, but its average benchmark score of 5721 includes a Geekbench Vulkan result of 5316, which is not measured for the Intel part. That Vulkan score pulls the NVIDIA average down significantly, making the average comparison (6554 versus 5721, a 14.5% gap) look larger than the head-to-head OpenCL gap of 7%.

The Intel part's wins come from its higher boost clock and its ability to achieve much higher pixel and texture rates despite having fewer shader units and TMUs. The NVIDIA part's wins, if any, would need to come from workloads that leverage its 960 shading units and 80 TMUs, or its dedicated 3 GB GDDR5 memory with 67.20 GB/s bandwidth. However, the recorded data does not include such a benchmark. In the only measured comparison, the Intel UHD Graphics P750 is the clear winner, and its average score reinforces that conclusion. The NVIDIA GeForce GTX 670MX remains a viable option in its own right, but the database does not show it outperforming the Intel part in any recorded test.