NVIDIA GeForce GT 735M vs NVIDIA GeForce GT 740 Comparison

# NVIDIA GeForce GT 735M vs NVIDIA GeForce GT 740

The NVIDIA GeForce GT 740 is the clear performance winner in this comparison, taking the only head-to-head benchmark with a 6% advantage over the GT 735M in Geekbench OpenCL scoring. The GT 740 posts a score of 3847 compared to the GT 735M’s 3616, a meaningful gap that reflects its more capable memory subsystem and higher compute throughput. Both cards sit in the 21st percentile of all GPUs, placing them in the same performance tier overall, but the GT 740’s edge in raw compute and memory bandwidth makes it the better choice for anyone weighing these two directly.

Head-to-Head Benchmarks

The single available direct comparison is Geekbench OpenCL, and the GT 740 wins decisively. It scores 3847 against the GT 735M’s 3616, a delta of -6% from the perspective of the GT 735M. That 231-point difference translates to roughly 6% higher performance, which is consistent with the GT 740’s hardware advantages: it runs at higher memory clocks, uses a wider memory bus, and delivers significantly more FP32 throughput. The GT 735M’s score of 3616 places it within a hair of the NVIDIA GeForce GTX 1050 (3629, -0.3%), meaning the gap to the GT 740 is roughly the same magnitude as the gap to a much newer discrete GPU. Meanwhile, the GT 740’s 3847 score sits 1.2% above the Intel HD Graphics P4600 (3389) and 3% above the Intel HD Graphics 530 (3332), showing it comfortably outperforms integrated-class solutions.

Looking at the broader benchmark landscape, the GT 735M’s average score across all tests is 3616, while the GT 740 averages 3431. That average is dragged down by the GT 740’s Geekbench Metal score of 2363 and Vulkan score of 4083, which are not directly comparable to the GT 735M’s single OpenCL result. In the only apples-to-apples test, the GT 740’s OpenCL score is 3847, confirming its superiority. The GT 735M’s nearest rival, the GTX 1050, scores 3629 (0.3% higher), while the GT 740’s nearest rival, the Quadro 2000M, scores 3434 (0.1% lower than the GT 740’s average). This shows the GT 740 performs slightly above a professional mobile Quadro of its era, while the GT 735M is essentially tied with a mainstream desktop GTX card in OpenCL.

The deltaPct values in the rival data are small across the board, indicating these are all tightly clustered GPUs. The GT 735M’s 0.6% edge over the RTX 5000 Mobile Ada Generation (3596) and GT 545 (3594) is negligible in practice, as is its 0.9% deficit to the AMD Radeon HD 6770 (3649). The GT 740’s 2.7% gap to the GeForce 920MX (3528) is the largest margin among its listed rivals, suggesting the GT 740 is meaningfully faster than that entry-level mobile chip. In head-to-head terms, the 6% OpenCL delta between the two reviewed cards is the single most important number, and it consistently favors the GT 740.

Where Each One Wins

The GT 740 wins the only benchmark where both cards were tested, so it takes the compute crown. Its Geekbench OpenCL score of 3847 reflects a GPU that can handle general-purpose compute tasks with more headroom than the GT 735M. The GT 740 also has additional benchmark results in Metal (2363) and Vulkan (4083), giving it a more complete profile across modern API workloads, though no direct GT 735M comparison exists for those tests. The GT 740’s higher pixel rate of 7.944 GPixel/s versus 5.024 GPixel/s for the GT 735M means it fills frames faster in rasterization-bound scenarios, and its texture rate of 31.78 GTexel/s versus 20.10 GTexel/s gives it a clear edge in texture-heavy scenes.

The GT 735M, by contrast, has no benchmark wins in this comparison. Its only advantage lies in efficiency and form factor: it draws 33 W versus the GT 740’s 64 W, and it is an IGP (integrated graphics processor) with no power connectors, while the GT 740 is a single-slot card requiring a 6-pin connector and a 250 W suggested PSU. For thin-and-light laptops, the GT 735M’s lower power draw and integrated nature make it the only practical choice, but that is a system-design consideration rather than a performance win. In raw compute, the GT 735M’s 482.3 GFLOPS FP32 is substantially below the GT 740’s 762.6 GFLOPS, a 58% deficit that shows up in the 6% OpenCL gap being smaller than the theoretical compute delta would suggest — likely due to memory bottlenecks on the GT 740’s side in certain workloads.

For gaming and graphics workloads, the GT 740’s 16 ROPs (versus 8 on the GT 735M) and 128-bit memory bus (versus 64-bit) provide a structural advantage that the benchmark data supports. The GT 740’s memory bandwidth of 80.19 GB/s is over 5.5 times the GT 735M’s 14.40 GB/s, which is a massive difference for texture streaming and high-resolution buffer operations. The GT 735M’s 2 GB DDR3 memory is double the GT 740’s 1 GB GDDR5 capacity, but the GT 740’s faster GDDR5 and wider bus more than compensate in bandwidth-sensitive tasks.

FAQ

Q: Which GPU is faster in OpenCL compute?

A: The GT 740, scoring 3847 versus the GT 735M’s 3616 in Geekbench OpenCL, a 6% advantage.

Q: Do both cards have the same number of shading units?

A: Yes, both have 384 shading units and 32 texture mapping units, but the GT 740 has 16 ROPs versus 8 on the GT 735M.

Q: What is the memory bandwidth difference?

A: The GT 740 delivers 80.19 GB/s over a 128-bit GDDR5 interface, while the GT 735M provides 14.40 GB/s over a 64-bit DDR3 interface.

Q: Which card has a higher pixel fill rate?

A: The GT 740 at 7.944 GPixel/s, compared to 5.024 GPixel/s for the GT 735M.

Q: Are these cards in the same performance percentile?

A: Yes, both rank in the 21st percentile of all GPUs, indicating they are similarly positioned in the overall performance hierarchy.

Q: What is the power consumption difference?

A: The GT 735M is rated at 33 W, while the GT 740 is rated at 64 W, requiring a 6-pin power connector and a 250 W suggested PSU.

Specification Differences

The two cards differ across nearly every major specification category. The GT 735M uses the GK208 chip with 1,020 million transistors on an 87 mm² die, while the GT 740 uses the GK107 chip with 1,270 million transistors on a 118 mm² die. The GT 735M has a base clock of 575 MHz and boost clock of 628 MHz, while the GT 740 has no listed base or boost clocks — only a memory clock of 1253 MHz (5 Gbps effective) versus the GT 735M’s 900 MHz (1800 Mbps effective). Memory configuration diverges sharply: the GT 735M has 2 GB DDR3 on a 64-bit bus with 14.40 GB/s bandwidth, while the GT 740 has 1024 MB GDDR5 on a 128-bit bus with 80.19 GB/s bandwidth.

Compute rates differ substantially: the GT 735M delivers 482.3 GFLOPS FP32, 20.10 GTexel/s texture rate, and 5.024 GPixel/s pixel rate, while the GT 740 delivers 762.6 GFLOPS FP32, 31.78 GTexel/s, and 7.944 GPixel/s. The GT 740 has 16 ROPs versus 8 on the GT 735M, though both have 384 shading units and 32 TMUs. Power and physical specs also differ: the GT 735M is an IGP at 33 W with no power connectors, while the GT 740 is a single-slot card at 64 W with one 6-pin connector and a 250 W suggested PSU. The GT 740 uses PCIe 3.0 x16, while the GT 735M uses PCIe 3.0 x8, and the GT 740 measures 145 mm (5.7 inches) in length with display outputs of 2x DVI and 1x mini-HDMI 1.4a, whereas the GT 735M’s outputs are portable-device dependent. The GT 740 has a launch MSRP of 89 USD.

Architecture Differences

Both cards are built on the 28 nm process at TSMC, but they represent different Kepler variants. The GT 735M uses Kepler 2.0 architecture with the GK208 chip, while the GT 740 uses the original Kepler architecture with the GK107 chip. The GT 735M has a transistor density of 11.7M per mm², slightly higher than the GT 740’s 10.8M per mm², reflecting the GK208’s more compact design. The GT 740’s larger die (118 mm² versus 87 mm²) accommodates double the ROP count (16 versus 8) and a wider memory interface (128-bit versus 64-bit), which are the key architectural differentiators.

The GT 740’s GDDR5 memory type is a significant architectural upgrade over the GT 735M’s DDR3, enabling the 5.5x bandwidth advantage. Both cards support DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175, so API compatibility is identical. The GT 740’s predecessor is GeForce 600, while the GT 735M’s predecessor is GeForce 600M, and their successors are GeForce 900 and GeForce 800M respectively. The GT 740 was released on 2014-05-28, while the GT 735M launched on 2013-03-31, making the GT 735M the older part by over a year.

The Verdict

The data points to a straightforward conclusion: the GT 740 is the stronger GPU in every measurable performance category. Its 6% OpenCL lead, 58% higher FP32 throughput, 5.5x memory bandwidth, and doubled ROP count make it the clear choice for any compute or graphics workload where the card can physically be installed. The GT 740’s additional benchmark results in Metal (2363) and Vulkan (4083) show it has broader API coverage, though those tests lack GT 735M equivalents for direct comparison. Its 89 USD launch MSRP is the only price reference available, and no such figure exists for the GT 735M.

The GT 735M’s only advantages are its 33 W power draw, IGP form factor with no power connectors, and double the memory capacity at 2 GB. For a compact, low-power laptop implementation, the GT 735M is the only feasible option — the GT 740’s 64 W TDP, single-slot size, and 6-pin connector demand a desktop chassis with adequate power delivery. However, anyone choosing between these two for a build where both fit should take the GT 740 without hesitation. Its 3847 OpenCL score places it 3% above the Intel HD Graphics 530 and 1.2% above the Intel HD Graphics P4600, while the GT 735M’s 3616 score ties it with the GTX 1050 and RTX 5000 Mobile Ada Generation (within 0.6%), showing the two cards occupy slightly different performance neighborhoods despite sharing the 21st percentile ranking. The verdict is clear: the GT 740 wins on performance, while the GT 735M wins only on power efficiency and integration suitability.