GPU Comparison

The NVIDIA GeForce MX110 and NVIDIA GeForce GT 635M are both end-of-life mobile graphics solutions from NVIDIA, but they represent different eras of the company's design philosophy. The MX110 is a Maxwell-based part from 2017, while the GT 635M is a Fermi-based part from 2012. The benchmark data shows a clear, if modest, performance gap between the two, with the MX110 winning the only head-to-head comparison available.

Head-to-Head Benchmarks

The sole direct comparison in the data is the Geekbench OpenCL test. Here, the NVIDIA GeForce MX110 scores 4255 points, while the NVIDIA GeForce GT 635M scores 3740 points. This gives the MX110 a decisive 13.8% advantage in raw compute throughput. This is a significant margin in a mobile environment where thermal and power constraints often narrow performance deltas. The MX110’s lead in this test is consistent with its more modern architecture and higher specifications.

Looking at the broader context, the MX110’s average benchmark score of 3834 places it at the 23rd percentile of all GPUs. Its nearest rivals include the NVIDIA GeForce GTX 650 (average score 3823, a delta of 0.3%) and the AMD Radeon R5 Graphics (average score 3883, a delta of -1.2%). This indicates the MX110 sits in a tight cluster of similarly-performing entry-level parts, where a few percentage points separate competitors. The GT 635M, with an average score of 3740, sits at the 22nd percentile, just one point lower. Its nearest rivals include the NVIDIA Quadro 3000M (average score 3718, a delta of 0.6%) and the NVIDIA GeForce GT 740M (average score 3717, a delta of 0.6%). The GT 635M is essentially tied with these parts, showing that it remains competitive within its own generation but is outclassed by the newer MX110.

The data suggests that the MX110 is not just faster, but also more consistent. The difference of 13.8% in the head-to-head OpenCL test is larger than the difference between the two parts' average scores, which is 2.5%. This implies that the MX110’s advantage may be more pronounced in compute-heavy workloads than in average gaming or general usage scenarios. For the GT 635M, its single benchmark score is its average, meaning there is no variance to analyze.

Architecture Differences

The two GPUs are built on fundamentally different architectures. The MX110 uses the Maxwell architecture on a 28 nm process node, manufactured by TSMC. In contrast, the GT 635M uses the older Fermi architecture on a 40 nm process node, also from TSMC. This process shrink is a major factor in the performance and efficiency differences between the two. The MX110 integrates 1,020 million transistors on a die size of 77 mm², resulting in a transistor density of 13.2 million transistors per square millimeter. The GT 635M, by comparison, has only 585 million transistors on a larger 116 mm² die, yielding a density of just 5.0 million transistors per square millimeter. This stark difference in density illustrates the generational leap in manufacturing capability.

The core configurations also differ significantly. The MX110 has 256 shading units, 16 texture mapping units (TMUs), and 8 render output units (ROPs). The GT 635M has only 96 shading units, 16 TMUs, and 4 ROPs. The MX110 has over 2.5 times the shading units and double the ROPs, which directly translates to higher pixel and texture throughput. The MX110 achieves a pixel rate of 8.048 GPixel/s and a texture rate of 16.10 GTexel/s. The GT 635M, with its lower core counts and clocks, manages only 1.900 GPixel/s and 7.600 GTexel/s, respectively. The FP32 floating-point performance tells a similar story: the MX110 delivers 515.1 GFLOPS, while the GT 635M delivers just 182.4 GFLOPS.

Memory technology is another major divergence. The MX110 uses 2 GB of GDDR5 memory on a 64-bit bus, providing a bandwidth of 40.10 GB/s. The GT 635M uses 2 GB of DDR3 memory on a 128-bit bus, but its effective bandwidth is only 28.80 GB/s. Despite having half the bus width, the MX110’s faster GDDR5 memory gives it a 39% bandwidth advantage. The MX110 also supports a newer PCIe 3.0 x4 interface, while the GT 635M uses PCIe 2.0 x16. In API support, the MX110 lists Vulkan 1.4, a feature the GT 635M does not list.

FAQ

Q: Which GPU is faster in compute benchmarks?

A: The NVIDIA GeForce MX110 is faster. In the Geekbench OpenCL test, it scores 4255 versus the GT 635M’s 3740, a 13.8% difference.

Q: How do their memory systems compare?

A: The MX110 uses 2 GB of GDDR5 on a 64-bit bus, achieving 40.10 GB/s bandwidth. The GT 635M uses 2 GB of DDR3 on a 128-bit bus, achieving 28.80 GB/s. The MX110 has higher total bandwidth despite a narrower bus.

Q: Which GPU has a higher transistor count?

A: The MX110 has 1,020 million transistors, while the GT 635M has 585 million. The MX110’s count is nearly double that of the GT 635M.

Q: What are the power consumption figures?

A: The MX110 has a TDP of 30 W, while the GT 635M has a TDP of 35 W. The MX110 is more power-efficient despite being the faster part.

Q: Do both GPUs support the same modern APIs?

A: Both support DirectX 12 (11_0) and OpenGL 4.6. However, the MX110 also lists Vulkan 1.4 support, while the GT 635M does not list any Vulkan version.

Q: What is the production status of these GPUs?

A: Both are listed as end-of-life products. The MX110 was released in 2017, and the GT 635M was released in 2012.

Specification Differences

The following table highlights only the fields where the two GPUs differ:

| Specification | NVIDIA GeForce MX110 | NVIDIA GeForce GT 635M |

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

| Architecture | Maxwell | Fermi |

| Process Node | 28 nm | 40 nm |

| Transistors | 1,020 million | 585 million |

| Die Size | 77 mm² | 116 mm² |

| Transistor Density | 13.2M / mm² | 5.0M / mm² |

| Base Clock | 978 MHz | Not listed |

| Boost Clock | 1006 MHz | Not listed |

| Memory Clock | 1253 MHz (5 Gbps effective) | 900 MHz (1800 Mbps effective) |

| Memory Type | GDDR5 | DDR3 |

| Memory Bus Width | 64 bit | 128 bit |

| Memory Bandwidth | 40.10 GB/s | 28.80 GB/s |

| Shading Units | 256 | 96 |

| ROPs | 8 | 4 |

| Pixel Rate | 8.048 GPixel/s | 1.900 GPixel/s |

| Texture Rate | 16.10 GTexel/s | 7.600 GTexel/s |

| FP32 Performance | 515.1 GFLOPS | 182.4 GFLOPS |

| TDP | 30 W | 35 W |

| Bus Interface | PCIe 3.0 x4 | PCIe 2.0 x16 |

| Vulkan Support | 1.4 | Not listed |

| Release Date | 2017-11-16 | 2012-03-21 |

| Predecessor | Not listed | GeForce 500M |

| Successor | Not listed | GeForce 700M |

The Verdict

The data is unambiguous: the NVIDIA GeForce MX110 is the superior graphics processor. It wins the only head-to-head benchmark by a substantial 13.8% margin, and its average benchmark score (3834) is higher than the GT 635M’s (3740). The MX110’s architectural advantages, a smaller process node, more shading units, faster memory, and higher fill rates, all contribute to this outcome. The GT 635M, while a capable part in its day, is hampered by its older Fermi architecture and slower DDR3 memory. The MX110 also achieves this higher performance at a lower TDP of 30 W compared to the GT 635M’s 35 W, making it a more efficient choice. For any user comparing these two, the MX110 is the clear pick based on all available benchmark data.

Where Each One Wins

The NVIDIA GeForce MX110 wins in every category where data is available. Its strengths lie in compute performance, as evidenced by the Geekbench OpenCL score of 4255. It also holds advantages in theoretical peak performance metrics like FP32 (515.1 GFLOPS) and pixel rate (8.048 GPixel/s). The MX110’s GDDR5 memory provides higher bandwidth, which is beneficial for memory-intensive tasks. Its support for Vulkan 1.4 also makes it more future-proof for modern applications.

The NVIDIA GeForce GT 635M has no benchmark wins in the provided data. However, its one advantage is the wider 128-bit memory bus, which, while paired with slower DDR3, could offer different latency characteristics in certain workloads. Its higher TDP of 35 W is a disadvantage, and its older PCIe 2.0 x16 interface, while having more lanes, is an older standard. The GT 635M is also the predecessor to the GeForce 700M series, making it a more dated solution overall. In essence, the GT 635M’s only potential claim is legacy compatibility or availability in older systems, but it cannot match the MX110 on any measured performance metric.