Intel UHD Graphics 710 vs NVIDIA GeForce GT 735M Comparison

Intel UHD Graphics 710 and NVIDIA GeForce GT 735M are both end-of-life integrated-class parts aimed at very different eras of computing. The data shows a single head-to-head benchmark result, with the GT 735M taking the win, but the underlying architectural and specification differences tell a more nuanced story about where each chip fits.

Head-to-Head Benchmarks

The only direct benchmark comparison available is Geekbench OpenCL, where the NVIDIA GeForce GT 735M scores 3616 against the Intel UHD Graphics 710's 3496. That gives the NVIDIA part a 3.3% lead. In practical terms, this is a narrow margin—well within the noise of real-world driver and thermal variation. Looking at the broader benchmark averages, the Intel part actually posts a higher mean score of 3792 across its two available tests, compared to the GT 735M's single-test average of 3616. That average is inflated by the Intel chip's strong Vulkan result of 4088, which is not a test the NVIDIA card has a score for.

The deltaPct values in the nearest rivals list further contextualize the OpenCL gap. The GT 735M's score is 0.6% ahead of an RTX 5000 Mobile Ada Generation and 0.6% ahead of a GeForce GT 545, while sitting 0.3% behind a GeForce GTX 1050. That is a tight cluster of results, meaning the GT 735M performs roughly on par with a wide range of older discrete and modern low-end parts. The Intel UHD 710, meanwhile, sits 0.8% behind a GeForce GTX 650 and 1.1% behind a GeForce MX110, but 1.4% ahead of a GeForce GT 635M and 2% ahead of a Quadro 3000M.

What this means is that neither chip is a performance powerhouse. The GT 735M edges out the Intel part in the one shared test, but the Intel chip's Vulkan score suggests it has a significant advantage in that specific API workload. If you are comparing raw compute throughput, the GT 735M's FP32 rating of 482.3 GFLOPS is clearly higher than the Intel part's 332.8 GFLOPS—a 45% difference. However, the Intel chip counters with a much higher pixel rate of 10.40 GPixel/s versus the GT 735M's 5.024 GPixel/s, more than doubling it. The texture rate tells the opposite story: the GT 735M's 20.10 GTexel/s nearly doubles the Intel part's 10.40 GTexel/s.

FAQ

Q: Which GPU wins the only direct benchmark comparison?

A: The NVIDIA GeForce GT 735M wins the Geekbench OpenCL test with a score of 3616 against the Intel UHD Graphics 710's 3496, a 3.3% margin.

Q: Does the Intel UHD 710 have any benchmark advantage?

A: Yes. The Intel part scores 4088 in Geekbench Vulkan, a test the GT 735M has no result for. This gives the Intel chip a higher average benchmark score of 3792 versus the NVIDIA card's 3616.

Q: How do these GPUs compare in raw floating-point performance?

A: The GT 735M is clearly ahead, with 482.3 GFLOPS of FP32 compute versus the Intel UHD 710's 332.8 GFLOPS. The NVIDIA part also supports FP16 at 482.3 GFLOPS natively, while the Intel chip's FP16 rating is 665.6 GFLOPS via a 2:1 ratio.

Q: What are the memory configurations of each?

A: The GT 735M has 2 GB of dedicated DDR3 memory on a 64-bit bus with 14.40 GB/s of bandwidth. The Intel UHD 710 uses System Shared memory, with bandwidth described as "System Dependent."

Q: Which GPU has a higher pixel fill rate?

A: The Intel UHD 710, at 10.40 GPixel/s, which is more than double the GT 735M's 5.024 GPixel/s. This suggests the Intel part may be better suited for fill-rate-bound tasks.

Q: What are the power requirements of each chip?

A: The Intel UHD 710 is rated at a 15 W TDP, while the GT 735M is rated at 33 W TDP. Both are integrated-class parts with no external power connectors.

Architecture Differences

These two GPUs come from completely different design philosophies and eras. The Intel UHD Graphics 710 is built on Alder Lake silicon using Intel's Generation 12.2 architecture on a 10 nm process node, fabricated by Intel itself. The NVIDIA GeForce GT 735M uses the GK208 chip based on Kepler 2.0 architecture on a 28 nm node from TSMC. The process node difference is stark: 10 nm versus 28 nm, giving Intel a significant density and efficiency advantage on paper.

The compute layout differs substantially. The Intel part has 128 shading units, 8 texture mapping units, and 8 ROPs. The GT 735M packs 384 shading units, 32 TMUs, and 8 ROPs. That is 3x the shading units and 4x the TMUs for NVIDIA, which explains its higher texture rate. However, the Intel chip makes up ground with its clock speeds: a base of 300 MHz and boost of 1300 MHz, versus the GT 735M's base of 575 MHz and boost of 628 MHz. The Intel boost clock is more than double the NVIDIA boost clock, which helps close the gap in certain workloads.

Memory architecture is another fundamental split. The Intel UHD 710 uses system-shared memory with no dedicated VRAM, relying on the host system's RAM. The GT 735M has 2 GB of dedicated DDR3 on a 64-bit bus, with memory clocked at 900 MHz (1800 Mbps effective) and bandwidth of 14.40 GB/s. This makes the GT 735M more self-sufficient but also ties it to older, slower memory standards. The Intel part's bandwidth is "System Dependent," meaning its performance scales with the platform's memory speed.

API support differs as well. The Intel UHD 710 supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The GT 735M supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. The Intel part has a more modern DirectX feature level and a newer Vulkan version, which likely explains its strong Vulkan benchmark result. The GT 735M's transistor count is listed at 1,020 million on a die size of 87 mm², giving a transistor density of 11.7M / mm². The Intel chip's transistor count and die size are not provided, but its 10 nm node suggests a much denser design.

Specification Differences

The core specifications diverge in nearly every measurable field. The Intel UHD 710 is fabricated on Intel's 10 nm process, while the GT 735M uses TSMC's 28 nm node. The Intel chip has a base clock of 300 MHz boosting to 1300 MHz, versus the NVIDIA part's 575 MHz base and 628 MHz boost. Shading units are 128 for Intel versus 384 for NVIDIA. TMUs are 8 versus 32. ROPs are identical at 8 each.

Memory is the biggest split. The Intel UHD 710 uses system-shared memory with no dedicated size, type, or bus width, while the GT 735M has 2 GB of DDR3 on a 64-bit bus with 14.40 GB/s bandwidth. The Intel chip's bandwidth is listed as "System Dependent," and its memory clock is also "System Shared." The GT 735M's memory runs at 900 MHz with 1800 Mbps effective speed.

Compute rates differ significantly. The Intel part posts 332.8 GFLOPS FP32, 665.6 GFLOPS FP16 (2:1), 10.40 GPixel/s pixel rate, and 10.40 GTexel/s texture rate. The GT 735M posts 482.3 GFLOPS FP32, no listed FP16 rate, 5.024 GPixel/s pixel rate, and 20.10 GTexel/s texture rate. TDP is another major difference: 15 W for Intel versus 33 W for NVIDIA. Both are listed as IGP slot width with no power connectors. The Intel part uses a Ring Bus interface, while the GT 735M uses PCIe 3.0 x8. Display outputs are motherboard dependent for Intel and portable device dependent for NVIDIA. Release dates are far apart: the Intel UHD 710 launched in January 2022, while the GT 735M launched in March 2013.

The Verdict

The data paints a clear picture of two chips designed for different purposes. The NVIDIA GeForce GT 735M wins the only directly comparable benchmark, the Geekbench OpenCL test, with a 3.3% margin. It also has a substantial advantage in raw FP32 compute (482.3 GFLOPS versus 332.8 GFLOPS) and texture rate (20.10 GTexel/s versus 10.40 GTexel/s). If your workload is compute-heavy or texture-bound, the GT 735M is the statistically stronger choice.

However, the Intel UHD Graphics 710 is not without merit. It dominates in pixel fill rate (10.40 GPixel/s versus 5.024 GPixel/s) and has a modern Vulkan 1.4 implementation that delivers a strong 4088 score in that benchmark—a test the GT 735M cannot even run. The Intel chip also draws less than half the power (15 W versus 33 W) and uses a much smaller process node (10 nm versus 28 nm). Its boost clock of 1300 MHz is over double the NVIDIA part's 628 MHz, which helps it punch above its weight in certain scenarios.

Benchmark percentiles are nearly identical: the UHD 710 sits at the 22nd percentile of all GPUs, while the GT 735M sits at the 21st. Both are firmly in entry-level territory. The GT 735M's average benchmark score of 3616 is lower than the UHD 710's 3792, but that average is based on one test versus two. The real takeaway is that these are both low-end parts with specific strengths, and the choice depends entirely on the workload.

Where Each One Wins

The NVIDIA GeForce GT 735M wins in scenarios that rely on compute throughput and texture processing. Its 45% advantage in FP32 GFLOPS makes it better suited for general-purpose compute tasks, physics simulations, and older games that favor raw shader power. The 4x TMU count (32 versus 8) gives it a massive edge in texture-heavy 3D rendering, making it the better pick for older DirectX 11 titles that rely on traditional texture sampling. The dedicated 2 GB DDR3 frame buffer also means it does not compete with the system for memory bandwidth, which can be a stability advantage in multitasking scenarios.

The Intel UHD Graphics 710 wins in fill-rate-bound and modern-API workloads. Its 10.40 GPixel/s pixel rate is more than double the GT 735M's 5.024 GPixel/s, making it better suited for resolution scaling, post-processing effects, and 2D compositing tasks. The Vulkan 1.4 support and strong 4088 Vulkan score indicate it handles modern graphics APIs far more efficiently than the GT 735M's older Vulkan 1.2.175 implementation. The much lower 15 W TDP also makes it a better fit for power-constrained systems, and the newer 10 nm process means it generates less heat for the same work.

For practical use, the GT 735M is the better choice if you are stuck with older software that favors OpenCL and DirectX 11. The Intel UHD 710 is the better choice for modern lightweight workloads, particularly those that leverage Vulkan. Neither chip is suitable for demanding gaming or professional rendering, but for basic desktop acceleration, media playback, and light productivity, the Intel part's modern feature set and lower power draw give it a longer useful life. The GT 735M's dedicated memory and higher compute ceiling make it a more capable legacy part for older game libraries.