GPU Comparison

# NVIDIA GeForce 830M vs NVIDIA GeForce GT 735M

The NVIDIA GeForce 830M and NVIDIA GeForce GT 735M are two mobile graphics solutions from different generations of NVIDIA's laptop lineup, separated by roughly a year of architectural evolution. The data shows a clear overall winner in the 830M, which posts an average benchmark score of 3957 against 3616 for the GT 735M, a 9.4% advantage. However, the two GPUs approach performance from very different design philosophies, one leaning on higher clock speeds, the other on wider execution resources, which makes their head-to-head comparison more nuanced than a simple score gap might suggest.

Where Each One Wins

The 830M is the outright winner in the only directly comparable benchmark, taking the Geekbench OpenCL test with a score of 4324 versus 3616 for the GT 735M, a 19.6% margin. This is the sole head-to-head data point, and it establishes the 830M as the faster GPU for compute-oriented workloads that stress OpenCL execution.

The GT 735M's case rests entirely on theoretical specifications rather than measured results. It carries 384 shading units and 32 texture mapping units, compared to 256 shading units and 16 TMUs on the 830M. In raw execution width, the GT 735M has 50% more shader processors and double the texture units. For workloads that scale perfectly with parallel resource count and are not bottlenecked by clock speed or memory bandwidth, the GT 735M could theoretically pull ahead, but no benchmark in the data confirms this.

The 830M counters with substantially higher clocks: a 1082 MHz base and 1150 MHz boost versus 575 MHz base and 628 MHz boost on the GT 735M. That is nearly a 2x clock advantage, which explains how fewer shaders can still produce more than 20% higher OpenCL performance. The 830M also holds the edge in pixel throughput at 9.200 GPixel/s versus 5.024 GPixel/s, despite both having 8 ROPs, because its higher clock rate drives more pixel operations per second.

In terms of percentile ranking among all GPUs, the 830M sits at the 24th percentile while the GT 735M sits at the 21st percentile. Both are entry-level mobile parts, but the 830M occupies a slightly higher tier in the overall performance distribution.

Architecture Differences

The two GPUs represent two distinct NVIDIA architectures. The 830M uses the GM108 chip built on the Maxwell architecture, while the GT 735M uses the GK208 chip built on Kepler 2.0. Both are manufactured by TSMC on a 28 nm process, and both pack exactly 1,020 million transistors. The die sizes differ, however: the 830M measures 77 mm² while the GT 735M is larger at 87 mm². This produces a higher transistor density on the 830M at 13.2M per mm² versus 11.7M per mm² on the GT 735M.

The memory subsystems are identical on paper: both use 2 GB of DDR3 with a 64-bit bus and 14.40 GB/s of bandwidth, running at 900 MHz (1800 Mbps effective). This means memory bandwidth is not a differentiator between the two, any performance gap must come from the compute cores and their clocks.

The shader configuration tells the story of two opposite design strategies. The GT 735M's Kepler architecture uses a wider configuration with 384 shading units and 32 TMUs. The 830M's Maxwell architecture uses a leaner setup with 256 shading units and 16 TMUs. Yet the Maxwell design's higher clocks, nearly double the base and boost frequencies, more than compensate for the reduced resource count. The FP32 compute throughput reflects this: the 830M delivers 588.8 GFLOPS while the GT 735M delivers 482.3 GFLOPS, a 22% advantage for the Maxwell part despite having one-third fewer shaders.

The texture rate slightly favors the GT 735M at 20.10 GTexel/s versus 18.40 GTexel/s on the 830M, thanks to its doubled TMU count partially offsetting the clock disadvantage. Pixel rate goes the other way, with the 830M's 9.200 GPixel/s outpacing the GT 735M's 5.024 GPixel/s by 83%.

Both GPUs support DirectX 12 (11_0) and OpenGL 4.6, but their Vulkan support differs: the 830M supports Vulkan 1.4 while the GT 735M supports the older Vulkan 1.2.175. Both are end-of-life products with no power connectors, integrated into laptops as IGP solutions, and both carry a 33 W TDP. The 830M was released on March 11, 2014, succeeding the GeForce 700M series, while the GT 735M was released on March 31, 2013, succeeding the GeForce 600M series and preceding the 800M generation.

Head-to-Head Benchmarks

The single head-to-head benchmark is Geekbench OpenCL, where the 830M scores 4324 against 3616 for the GT 735M, a 19.6% delta. This is a substantial margin that validates the Maxwell architecture's efficiency advantage over Kepler in real compute workloads.

To put that score in context, the 830M's nearest rivals in the overall benchmark database include the AMD Radeon R5 M420 at 3956 (0% delta), the NVIDIA GeForce GT 745M at 3953 (0.1% delta), the NVIDIA Quadro K2000 at 3964 (-0.2% delta), and the AMD Radeon HD 6850 X2 at 3977 (-0.5% delta). The 830M essentially trades blows with these parts, sitting within 0.5% of all four.

The GT 735M's nearest rivals paint a different picture. Its 3616 average score puts it near the NVIDIA GeForce GTX 1050 at 3629 (-0.3% delta), the NVIDIA RTX 5000 Mobile Ada Generation at 3596 (0.6% delta), the NVIDIA GeForce GT 545 at 3594 (0.6% delta), and the AMD Radeon HD 6770 at 3649 (-0.9% delta). The presence of much newer and much older hardware in this rival group highlights how the GT 735M's score sits in a crowded mid-low performance band.

The 19.6% OpenCL gap between the two GPUs is larger than the 9.4% gap in their average benchmark scores, suggesting the 830M's advantage may be most pronounced specifically in OpenCL compute tasks. The 830M also has a second benchmark result, Geekbench Vulkan at 3590, which the GT 735M lacks entirely. This Vulkan result is notably lower than its OpenCL score, indicating the 830M's compute performance varies significantly by API.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The NVIDIA GeForce 830M has an average benchmark score of 3957, while the NVIDIA GeForce GT 735M scores 3616. This gives the 830M a 9.4% advantage overall.

Q: How much faster is the 830M in OpenCL compute?

A: In the Geekbench OpenCL test, the 830M scores 4324 versus 3616 for the GT 735M, making it 19.6% faster in this specific workload.

Q: Does the GT 735M have any advantages over the 830M?

A: The GT 735M has more shading units (384 versus 256) and more texture mapping units (32 versus 16), giving it a higher texture fill rate of 20.10 GTexel/s compared to 18.40 GTexel/s on the 830M.

Q: Are both GPUs the same in terms of memory?

A: Yes, both use 2 GB of DDR3 memory with a 64-bit bus width and 14.40 GB/s of bandwidth, running at 900 MHz (1800 Mbps effective).

Q: Which GPU was released more recently?

A: The NVIDIA GeForce 830M was released on March 11, 2014, while the NVIDIA GeForce GT 735M was released on March 31, 2013, making the 830M nearly a year newer.

Q: Do both GPUs support the same APIs?

A: Both support DirectX 12 (11_0) and OpenGL 4.6, but the 830M supports Vulkan 1.4 while the GT 735M supports Vulkan 1.2.175.

The Verdict

The data points decisively toward the NVIDIA GeForce 830M for anyone choosing between these two mobile GPUs. Its 19.6% OpenCL advantage and 9.4% average score lead are not marginal, they represent a meaningful generational improvement. The 830M achieves this with fewer shading units and TMUs, relying instead on a nearly 2x clock speed advantage and the more compute-efficient Maxwell architecture.

The GT 735M's only theoretical strengths are its wider shader configuration and higher texture rate. For workloads that are heavily texture-bound and scale poorly with clock speed, the GT 735M could match or slightly exceed the 830M, the data shows 20.10 GTexel/s versus 18.40 GTexel/s. But no benchmark result confirms this advantage in practice.

For gaming and general GPU compute, the 830M is the clear choice. Its higher pixel rate (9.200 GPixel/s versus 5.024 GPixel/s) and higher FP32 throughput (588.8 GFLOPS versus 482.3 GFLOPS) point to better real-world performance across most tasks. The 830M also benefits from newer architecture support, including Vulkan 1.4 versus 1.2.175 on the GT 735M.

The GT 735M should only be considered if texture-heavy workloads dominate and the 20.10 GTexel/s rate is specifically needed, a narrow use case that the benchmark data does not validate. For all measured scenarios, the 830M wins.

Specification Differences

| Specification | NVIDIA GeForce 830M | NVIDIA GeForce GT 735M |

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

| Architecture | Maxwell | Kepler 2.0 |

| Chip | GM108 | GK208 |

| Generation | GeForce 800M | GeForce 700M |

| Die Size | 77 mm² | 87 mm² |

| Transistor Density | 13.2M / mm² | 11.7M / mm² |

| Base Clock | 1082 MHz | 575 MHz |

| Boost Clock | 1150 MHz | 628 MHz |

| Shading Units | 256 | 384 |

| TMUs | 16 | 32 |

| Pixel Rate | 9.200 GPixel/s | 5.024 GPixel/s |

| Texture Rate | 18.40 GTexel/s | 20.10 GTexel/s |

| FP32 | 588.8 GFLOPS | 482.3 GFLOPS |

| Vulkan Version | 1.4 | 1.2.175 |

| Release Date | 2014-03-11 | 2013-03-31 |

| Predecessor | GeForce 700M | GeForce 600M |

| Successor | GeForce 900M | GeForce 800M |