NVIDIA GeForce GT 735M vs NVIDIA GeForce GTX 460M Comparison

Head-to-Head Benchmarks

The recorded data contains a single head-to-head comparison between the NVIDIA GeForce GTX 460M and the NVIDIA GeForce GT 735M, using the Geekbench OpenCL benchmark. The results are decisive: the GTX 460M scores 4282 points, while the GT 735M scores 3616 points. This gives the GTX 460M a winning margin of 18.4%. In absolute terms, the GTX 460M is ahead by 666 points, a substantial gap that places it in a clearly higher performance tier.

Looking at the wider database context, the GTX 460M sits at the 25th percentile of all GPUs, while the GT 735M sits at the 21st percentile. This difference, while only four percentile points, is consistent with the 18.4% benchmark delta. The GTX 460M's average benchmark score of 4282 places it among rivals such as the AMD FirePro W2100 (4295, a mere 0.3% higher), the AMD Radeon Vega 3 (4268, 0.3% lower), and the NVIDIA Quadro K3000M (4241, 1% lower). Notably, the GTX 460M is only 1.2% behind the NVIDIA GeForce RTX 4070 GDDR6 (4335), a modern high-end part, which underscores how competitive the older Fermi-based chip remains in this specific compute workload.

The GT 735M's average score of 3616 places it near the NVIDIA GeForce GTX 1050 (3629, 0.3% higher), the NVIDIA RTX 5000 Mobile Ada Generation (3596, 0.6% lower), and the NVIDIA GeForce GT 545 (3594, 0.6% lower). It also trails the AMD Radeon HD 6770 (3649) by 0.9%. The delta between the two cards is not a near-miss; it is a clear, consistent advantage for the GTX 460M across the entire benchmark spectrum.

The single benchmark result is corroborated by the internal specifications. The GTX 460M delivers 518.4 GFLOPS of FP32 compute, compared to the GT 735M's 482.3 GFLOPS, a 7.5% raw compute advantage. The texture fill rate is also slightly higher on the GTX 460M: 21.60 GTexel/s versus 20.10 GTexel/s. Pixel throughput is closer, with the GTX 460M at 5.400 GPixel/s versus the GT 735M's 5.024 GPixel/s. The memory subsystem is where the gap widens dramatically. The GTX 460M uses 1536 MB of GDDR5 on a 192-bit bus, yielding 60.00 GB/s of bandwidth, while the GT 735M uses 2 GB of DDR3 on a 64-bit bus, yielding only 14.40 GB/s. This 4.17x bandwidth advantage for the GTX 460M is the primary driver of its benchmark superiority, as OpenCL workloads often scale with memory throughput.

The Verdict

The data is unambiguous: the NVIDIA GeForce GTX 460M is the faster GPU in this comparison. It wins the only head-to-head benchmark by 18.4%, and its average benchmark score of 4282 is 18.4% higher than the GT 735M's 3616. If the selection criterion is raw compute performance in OpenCL, the GTX 460M is the correct choice. It also holds a percentile advantage, ranking higher than 25% of all GPUs compared to the GT 735M's 21%.

However, the GT 735M is not without merit, but its advantages are not in raw speed. It consumes less power: 33 W versus 50 W, a 34% reduction. It is built on a newer 28 nm process node versus 40 nm, and it supports a newer PCIe interface (3.0 x8 versus 2.0 x16). It also has a larger memory capacity of 2 GB versus 1536 MB, which can matter in certain memory-hungry applications, though its DDR3 memory and 64-bit bus severely limit the practical benefit. For users prioritizing battery life and thermals in a thin laptop, the GT 735M is the more efficient part. For anyone prioritizing execution speed in compute tasks, the GTX 460M is the definitive winner.

The benchmark data suggests that the GTX 460M's older Fermi architecture, with its wider memory bus and GDDR5 memory, outperforms the Kepler-based GT 735M despite the latter's higher shading unit count (384 versus 192). This is a classic case where memory bandwidth dominates raw shader count. The verdict from the database is clear: the GTX 460M wins on performance, the GT 735M wins on efficiency.

Architecture Differences

The two GPUs come from different architectural generations. The GTX 460M is based on the GF106 chip, using the Fermi architecture, and belongs to the GeForce 400M generation. The GT 735M is based on the GK208 chip, using the Kepler 2.0 architecture, and belongs to the GeForce 700M generation. This generational gap is significant: Fermi was NVIDIA's first truly compute-oriented architecture, while Kepler was optimized for power efficiency and higher clock speeds per watt.

The process technology differs substantially. The GTX 460M is fabricated on a 40 nm process at TSMC, with 1,170 million transistors on a 238 mm² die, giving a transistor density of 4.9 million per mm². The GT 735M is fabricated on a 28 nm process, also at TSMC, with 1,020 million transistors on a much smaller 87 mm² die, giving a transistor density of 11.7 million per mm². The newer node allows the GT 735M to pack nearly the same transistor count into less than half the die area, which explains its lower power draw.

The core configurations differ in notable ways. The GTX 460M has 192 shading units, 32 TMUs, and 24 ROPs. The GT 735M has 384 shading units, which is double, but only 32 TMUs and 8 ROPs. The higher shading unit count on the GT 735M does not translate into a performance win, likely due to the severe memory bottleneck. The GTX 460M's ROP count is three times higher, which explains its higher pixel rate of 5.400 GPixel/s versus 5.024 GPixel/s.

Memory architecture is the most dramatic differentiator. The GTX 460M uses 1536 MB of GDDR5 with a 192-bit bus, running at 625 MHz (2.5 Gbps effective), yielding 60.00 GB/s. The GT 735M uses 2 GB of DDR3 with a 64-bit bus, running at 900 MHz (1800 Mbps effective), yielding 14.40 GB/s. The GTX 460M has over four times the memory bandwidth, which is the decisive factor in the benchmark outcome.

Clock speeds also differ. The GTX 460M has no listed base or boost clock, only its memory clock. The GT 735M has a base clock of 575 MHz and a boost clock of 628 MHz. Despite having higher clocks, the GT 735M cannot overcome its memory deficit. The GTX 460M supports PCIe 2.0 x16, while the GT 735M supports PCIe 3.0 x8, though this interface difference is unlikely to affect the benchmark result. Both support DirectX 12 (11_0) and OpenGL 4.6, but the GT 735M adds Vulkan 1.2.175 support, which the GTX 460M lacks.

FAQ

Q: Which GPU is faster in the Geekbench OpenCL benchmark?

A: The NVIDIA GeForce GTX 460M is faster, scoring 4282 points versus the GT 735M's 3616 points, an 18.4% advantage.

Q: How much memory bandwidth does each GPU have?

A: The GTX 460M has 60.00 GB/s of bandwidth from its 192-bit GDDR5 memory, while the GT 735M has 14.40 GB/s from its 64-bit DDR3 memory.

Q: Which GPU is more power-efficient?

A: The GT 735M is more power-efficient, with a TDP of 33 W compared to the GTX 460M's 50 W, a 34% reduction in power draw.

Q: Do both GPUs support DirectX 12?

A: Yes, both support DirectX 12 (11_0) and OpenGL 4.6. The GT 735M additionally supports Vulkan 1.2.175, which the GTX 460M does not.

Q: What is the memory capacity difference?

A: The GT 735M has 2 GB of memory, while the GTX 460M has 1536 MB. The GT 735M has more capacity, but its memory type and bus width are far slower.

Q: How do these GPUs rank against all other GPUs?

A: The GTX 460M ranks at the 25th percentile, while the GT 735M ranks at the 21st percentile. The GTX 460M is also within 1.2% of the RTX 4070 GDDR6 in the database, while the GT 735M trails the GTX 1050 by 0.3%.

Where Each One Wins

The GTX 460M wins decisively in raw compute performance. Its 18.4% benchmark lead is substantial, and it holds advantages in FP32 compute (518.4 GFLOPS versus 482.3 GFLOPS), texture fill rate (21.60 GTexel/s versus 20.10 GTexel/s), and pixel rate (5.400 GPixel/s versus 5.024 GPixel/s). The memory bandwidth advantage of 60.00 GB/s versus 14.40 GB/s makes it the clear choice for any workload that is memory-bound, such as large matrix operations, image processing, or any OpenCL compute task. Its higher ROP count (24 versus 8) also suggests better performance in fill-rate-limited scenarios, such as high-resolution rendering.

The GT 735M wins in efficiency and platform compatibility. Its lower TDP of 33 W versus 50 W makes it suitable for thinner laptops with smaller cooling solutions. It supports PCIe 3.0 x8, which is a newer interface than the GTX 460M's PCIe 2.0 x16, making it more compatible with modern motherboards. It has double the memory capacity (2 GB versus 1536 MB), which could be beneficial in applications that require large memory footprints but do not heavily stress bandwidth. The Vulkan 1.2.175 support is a feature advantage, enabling modern API usage that the GTX 460M cannot access.

For gaming workloads, the GTX 460M's higher memory bandwidth and pixel rate are likely to provide a smoother experience at moderate settings, while the GT 735M may struggle due to its limited bandwidth. For office productivity and media playback, the GT 735M's lower power draw and newer architecture make it the more practical choice.

Specification Differences

The following table lists only the fields where the two GPUs differ, based on the recorded data:

| Specification | NVIDIA GeForce GTX 460M | NVIDIA GeForce GT 735M |

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

| Architecture | Fermi | Kepler 2.0 |

| Generation | GeForce 400M | GeForce 700M |

| Process Node | 40 nm | 28 nm |

| Transistors | 1,170 million | 1,020 million |

| Die Size | 238 mm² | 87 mm² |

| Transistor Density | 4.9M / mm² | 11.7M / mm² |

| Memory Clock | 625 MHz (2.5 Gbps effective) | 900 MHz (1800 Mbps effective) |

| Base Clock | Not listed | 575 MHz |

| Boost Clock | Not listed | 628 MHz |

| Memory Size | 1536 MB | 2 GB |

| Memory Type | GDDR5 | DDR3 |

| Memory Bus Width | 192 bit | 64 bit |

| Memory Bandwidth | 60.00 GB/s | 14.40 GB/s |

| Shading Units | 192 | 384 |

| ROPs | 24 | 8 |

| Pixel Rate | 5.400 GPixel/s | 5.024 GPixel/s |

| Texture Rate | 21.60 GTexel/s | 20.10 GTexel/s |

| FP32 Compute | 518.4 GFLOPS | 482.3 GFLOPS |

| TDP | 50 W | 33 W |

| Slot Width | MXM Module | IGP |

| Bus Interface | PCIe 2.0 x16 | PCIe 3.0 x8 |

| Vulkan Support | Not listed | 1.2.175 |

| Release Date | 2010-09-02 | 2013-03-31 |

| Predecessor | GeForce 300M | GeForce 600M |

| Successor | GeForce 500M | GeForce 800M |

| Average Benchmark Score | 4282 | 3616 |

| Percentile vs All GPUs | 25 | 21 |

| Geekbench OpenCL Score | 4282 | 3616 |

| Head-to-Head Winner | Yes (18.4% delta) | No |