NVIDIA GeForce GTX 765M

The NVIDIA GeForce GTX 765M is a Kepler-architecture mobile GPU from the GeForce 700M generation, built on TSMC's 28 nm process with 2,540 million transistors on a 221 mm² die. It targets the upper-midrange laptop segment of its era, and its benchmark data places it at the 31st percentile of all GPUs, indicating a modest standing in the modern landscape. With a base clock of 797 MHz and a boost clock of 863 MHz, the GTX 765M delivers an average benchmark score of 5,526, a figure that places it in a tightly contested cluster of comparable mobile parts.

Benchmark Performance

The GTX 765M's average benchmark score of 5,526 is a composite measure derived from its Geekbench results across three APIs: 2,612 in Metal, 7,251 in OpenCL, and 6,714 in Vulkan. The wide spread between Metal and OpenCL scores suggests that the GPU's raw compute capabilities are more fully realized in OpenCL workloads, while the Vulkan result indicates a strong showing in modern low-level API scenarios. This variance hints at driver maturity differences or architectural strengths in specific compute paths, rather than a uniform performance profile.

Relative to its nearest rivals, the GTX 765M sits in a precarious position. It trails the AMD FirePro M4000 by a razor-thin margin of 0.1%, a difference so small it is effectively a statistical tie. The NVIDIA Quadro M4000 is 0.8% ahead, while the AMD Radeon HD 8790M is 1.3% behind. The most significant gap is against the NVIDIA GeForce MX130, which leads by 1.9%. These deltas are all within a narrow band of roughly 3 percentage points, meaning the GTX 765M is neither a clear winner nor a definitive loser in its immediate competitive set—it is a middle-of-the-pack performer where minor driver optimizations or thermal variations could flip the order.

The FP32 performance of 1,325.6 GFLOPS provides a theoretical ceiling that the benchmark scores only partially capture. The pixel rate of 13.81 GPixel/s and texture rate of 55.23 GTexel/s are modest figures that reflect the 16 ROPs and 64 TMUs, suggesting that the GPU can handle basic rasterization but will strain under heavy fill-rate demands. The data implies that the GTX 765M is best suited for older titles or lower-detail settings, as its compute throughput does not translate into consistently high frame rates in modern, GPU-intensive workloads.

Ray Tracing and Feature Set

The GTX 765M has no dedicated ray tracing cores and no tensor cores, as these are absent from the FACT PACK specifications. This places the GPU firmly in the pre-ray-tracing era, where such features were not part of the consumer graphics landscape. Consequently, the card relies entirely on traditional rasterization techniques, and any ray-traced effects would have to be implemented through compute shaders, which would incur a significant performance penalty given the GPU's limited compute resources.

API support is a mixed bag. The GPU supports DirectX 12 (11_0), which is the feature level for the DirectX 12 API, indicating compatibility with the API but not the full DirectX 12 Ultimate feature set. OpenGL 4.6 and Vulkan 1.2.175 are both supported, offering modern low-level access for titles that utilize these APIs. The Vulkan score of 6,714 is notably higher than the Metal score, suggesting that Vulkan workloads are better optimized for this architecture, potentially due to Kepler's design maturity in that API's driver stack. For gamers, this means titles leveraging Vulkan could see better performance than those using DirectX 11, which is the API most games of this GPU's era would have used.

Who Should Consider It

Given the benchmark scores, the GTX 765M is a candidate for users playing older games or esports titles at 720p or 1080p with low-to-medium settings. The 31st percentile ranking means it outperforms roughly a third of all GPUs, which in practical terms translates to playable frame rates in titles from around its 2013 release window, but struggles with modern AAA releases. The 2 GB VRAM capacity is a limiting factor at 1080p in newer games, as texture-heavy scenes can exceed this budget, leading to stuttering or reduced texture quality.

For 720p gaming, the GPU is more viable, as the lower resolution reduces the memory and fill-rate demands. The 1.3% advantage over the AMD Radeon HD 8790M indicates that in this niche, the GTX 765M can hold its own against a contemporary rival. However, users seeking to play the latest games at high settings will find the GPU inadequate, as the data shows a performance profile that is simply too weak for such demands. The absence of ray tracing support further narrows its suitability, making it a poor choice for any title that relies on hardware-accelerated ray tracing.

How It Compares

AMD FirePro M4000: The GTX 765M trails this rival by just 0.1%, making the two effectively identical in average performance. This is a virtual dead heat, where the outcome of any given workload could swing either way depending on driver updates or thermal conditions. The FirePro M4000, despite being a workstation-class part, offers no tangible advantage in the benchmark data.

NVIDIA Quadro M4000: A 0.8% lead for the Quadro M4000 places it slightly ahead, but this margin is within the noise of typical benchmark variance. The Quadro M4000's workstation pedigree does not translate into a meaningful performance edge in these compute-focused tests, suggesting that the GTX 765M is not significantly disadvantaged in raw throughput.

AMD Radeon HD 8790M: The GTX 765M holds a 1.3% advantage over this rival, which is the only rival it beats in the comparison set. This is a modest but real margin, indicating that the GTX 765M has a slight edge in average performance over this contemporary AMD part, though the gap is small enough that specific game optimizations could reverse it.

NVIDIA GeForce MX130: The MX130 leads by 1.9%, the largest delta in the group. This newer part, while not a high-end GPU, outperforms the GTX 765M by a noticeable margin. The data suggests that generational efficiency improvements in the MX130's architecture provide a tangible, if modest, performance benefit over the older Kepler design.

Memory Subsystem

The GTX 765M is equipped with 2 GB of GDDR5 memory on a 128-bit bus, yielding a bandwidth of 64.13 GB/s. The memory clock is 1002 MHz, which translates to 4 Gbps effective. This bandwidth figure is a critical bottleneck for the GPU, as it is relatively low by modern standards and limits the rate at which texture and geometry data can be fed to the shading units.

At high resolutions, such as 1440p or above, the 2 GB VRAM capacity is a severe constraint. Modern games often require more than 2 GB for high-resolution textures, and exceeding this limit forces the GPU to use system memory over the PCIe bus, which is significantly slower and causes stuttering. The 128-bit bus width further exacerbates the issue, as it provides fewer memory channels compared to wider buses, making the 64.13 GB/s bandwidth the effective ceiling for data throughput. For 1080p gaming, this memory subsystem is workable for older titles but will struggle with newer games that assume larger VRAM pools and higher bandwidth. The data implies that the memory configuration is a primary reason the GTX 765M cannot scale to modern gaming demands, even if its compute capabilities were sufficient.

FAQ

Q: How does the GTX 765M perform in Geekbench Vulkan tests?

A: It scores 6,714 in the Geekbench Vulkan test, which is notably higher than its Metal score of 2,612, indicating stronger performance in Vulkan-based workloads.

Q: What is the GPU's transistor count and die size?

A: The GK106 chip contains 2,540 million transistors on a 221 mm² die, fabricated on a 28 nm process at TSMC.

Q: Does the GTX 765M support DirectX 12 Ultimate?

A: No, it supports DirectX 12 (11_0), which is the feature level 11_0 subset of the DirectX 12 API, not the full Ultimate feature set.

Q: What is the average benchmark score of the GTX 765M?

A: The average benchmark score is 5,526, drawn from its Geekbench Metal, OpenCL, and Vulkan results.

Q: How does the GTX 765M compare to the NVIDIA GeForce MX130?

A: The MX130 is 1.9% ahead of the GTX 765M in average score, making it the closest rival that the GTX 765M trails by the largest margin in its comparison set.

Q: What is the memory bandwidth of the GTX 765M?

A: The memory bandwidth is 64.13 GB/s, provided by 2 GB of GDDR5 memory on a 128-bit bus.

Power and Cooling

The GTX 765M has a thermal design power (TDP) of 75 W, which is a modest figure for a mobile GPU of its era. This power envelope allows for a relatively slim cooling solution, and the GPU is designed as an MXM Module with a slot width of MXM-B (3.0). The power connectors are listed as "None," meaning the module draws all its power from the MXM slot itself, simplifying integration into laptops that support this form factor.

There is no suggested PSU specification in the FACT PACK, so no recommendation can be made in that regard. The lack of external power connectors indicates that the GPU is intended for systems where the MXM slot can supply sufficient power, which is typical for midrange mobile parts. The 75 W TDP is low enough that a capable air cooler, such as those found in thicker gaming laptops, should handle the thermal load without excessive noise or throttling. The absence of a power connector also means that users do not need to manage additional cabling, making the GTX 765M a straightforward upgrade path for compatible MXM systems, provided the laptop's BIOS and cooling can accommodate it.