NVIDIA GeForce GTX 760 vs NVIDIA GeForce GTX 870M Comparison

The NVIDIA GeForce GTX 870M and the NVIDIA GeForce GTX 760 are both built on the Kepler architecture, using the same GK104 chip, yet they target fundamentally different segments of the market. The 870M is a mobile part designed for laptops, while the 760 is a desktop card. Benchmark data shows the mobile 870M holds a 5.3% lead in average benchmark score (9959 vs. 9458), despite the desktop card's higher clock speeds and wider memory bus. This analysis examines the architectural differences, benchmark results, and specification gaps to determine which GPU is the better choice for specific use cases.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 870M has a higher average benchmark score of 9959, compared to the NVIDIA GeForce GTX 760's 9458. This places the 870M in the 48th percentile of all GPUs, while the 760 sits in the 46th percentile.

Q: How much faster is the GTX 870M in the Geekbench Metal test?

A: The GTX 870M scores 7288 in Geekbench Metal, which is 61.1% higher than the GTX 760's score of 4524. This is the largest performance delta between the two cards in any benchmark.

Q: What is the difference in memory bandwidth between the two cards?

A: The GTX 760 has significantly higher memory bandwidth at 192.3 GB/s, thanks to its 256-bit bus and 6 Gbps effective memory speed. The GTX 870M, with a 192-bit bus and 5 Gbps effective speed, delivers 120.0 GB/s.

Q: Do both cards support the same DirectX version?

A: Yes, both the GTX 870M and the GTX 760 support DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. They share identical API feature sets.

Q: Which card has a higher transistor count?

A: Both cards have identical transistor counts of 3,540 million on a 294 mm² die size, as they are both based on the GK104 chip manufactured on TSMC's 28 nm process.

Q: What is the TDP difference between the two?

A: The GTX 870M has a TDP of 100 W, while the GTX 760 has a TDP of 170 W. The mobile card is significantly more power-efficient, drawing 70 W less power.

Architecture Differences

Both GPUs share the same fundamental architecture, being built on NVIDIA's Kepler design with the GK104 chip. They are manufactured on the same 28 nm process at TSMC, with identical transistor counts of 3,540 million and the same die size of 294 mm². The transistor density is also identical at 12.0M per mm². This means the underlying compute architecture is largely the same, with differences emerging in how the resources are configured.

The most striking difference lies in the core configuration. The GTX 870M features 1344 shading units, 112 texture mapping units (TMUs), and 24 render output units (ROPs). In contrast, the GTX 760 has fewer shading units at 1152 and fewer TMUs at 96, but it compensates with more ROPs at 32. This configuration suggests the 870M is optimized for compute-heavy workloads with more parallel processors, while the 760 dedicates more silicon to pixel throughput and rasterization.

Clock speeds also differ substantially. The GTX 760 runs at a base clock of 980 MHz with a boost of 1032 MHz, while the GTX 870M operates at a lower 941 MHz base and 967 MHz boost. The desktop card's higher clocks are typical of a part with more thermal headroom, but the mobile card's higher core count helps it overcome this deficit in raw compute throughput. The FP32 performance tells this story: the 870M delivers 2.599 TFLOPS versus the 760's 2.378 TFLOPS, meaning the extra shading units more than compensate for the lower clock speed.

Memory architecture is another key divergence. The GTX 870M uses 3 GB of GDDR5 on a 192-bit bus, yielding 120.0 GB/s of bandwidth. The GTX 760 uses 2 GB of GDDR5 on a 256-bit bus, achieving 192.3 GB/s. This is a significant advantage for the desktop card, offering 60% more memory bandwidth. The 870M's memory runs at 1250 MHz (5 Gbps effective), while the 760's runs at 1502 MHz (6 Gbps effective), contributing to the bandwidth gap.

Power delivery and physical design differ as expected for their respective platforms. The 870M is an MXM module with no power connectors, drawing 100 W, while the 760 is a dual-slot card requiring 2x 6-pin power connectors and a 450 W suggested PSU, drawing 170 W. The desktop card also features a 241 mm (9.5 inches) length and dedicated display outputs (2x DVI, 1x HDMI 1.4a, 1x DisplayPort 1.2), whereas the mobile part's outputs are "Portable Device Dependent."

Head-to-Head Benchmarks

The benchmark data shows a clear, if nuanced, picture. In the two Geekbench tests available, the GTX 870M wins both, taking the head-to-head tally 2-0. The most decisive victory comes in the Geekbench Metal test, where the 870M scores 7288 against the 760's 4524. This 61.1% delta is substantial and indicates that the mobile GPU's higher shading unit count (1344 vs. 1152) provides a major advantage in this particular API's workload. Metal is a low-level graphics API, and the 870M's additional compute units clearly scale well.

The Geekbench OpenCL test is closer, with the 870M scoring 12630 versus the 760's 11299. The delta here is 11.8%, still a win for the mobile card, but far less dramatic. OpenCL is a general-purpose compute benchmark, and the results suggest that while the 870M has an edge, the 760's higher memory bandwidth (192.3 GB/s vs. 120.0 GB/s) helps it narrow the gap. The 760's faster clock speeds (980 MHz base vs. 941 MHz) also play a role in keeping the desktop card competitive.

It is notably the GTX 760 has a third benchmark result, a Geekbench Vulkan score of 12551, which has no direct comparison in the 870M's data set. While this score is higher than the 870M's OpenCL result, it cannot be directly compared across APIs. The absence of a Vulkan score for the 870M means the data is incomplete, but the two tests that do overlap favor the mobile part consistently.

Looking at relative performance against other GPUs, the 870M's average score of 9959 places it 1.1% ahead of the NVIDIA Quadro 6000 and 0.5% behind the AMD Radeon Pro 5300M. The 760's average of 9458 puts it 1.8% ahead of the NVIDIA GeForce GTX 465 and 0.2% behind the NVIDIA GeForce GTX TITAN BLACK. These rival comparisons show that both cards sit in a similar performance tier, but the 870M holds a slight edge in aggregate.

Specification Differences

The specification sheets reveal several key differences between the two GPUs, primarily driven by their intended platforms. The most obvious is memory configuration: the 870M offers 3 GB of VRAM versus the 760's 2 GB, giving the mobile card more capacity for large textures. However, the 760's 256-bit bus and 6 Gbps effective memory speed deliver 192.3 GB/s of bandwidth, compared to the 870M's 192-bit bus and 5 Gbps speed for 120.0 GB/s. This is a clear trade-off between capacity and throughput.

Core counts differ, with the 870M featuring 1344 shading units, 112 TMUs, and 24 ROPs, while the 760 has 1152 shading units, 96 TMUs, and 32 ROPs. The 870M has 16.7% more shading units and TMUs, but the 760 has 33.3% more ROPs. This leads to different rate limits: the 870M achieves 27.08 GPixel/s pixel rate and 108.3 GTexel/s texture rate, versus the 760's 24.77 GPixel/s and 99.07 GTexel/s. The mobile card wins both rate metrics despite lower clocks.

Clock speeds favor the desktop part. The 760 runs at 980 MHz base and 1032 MHz boost, while the 870M runs at 941 MHz base and 967 MHz boost. The 760 also has faster memory clocks at 1502 MHz (6 Gbps effective) versus the 870M's 1250 MHz (5 Gbps effective). FP32 compute favors the 870M at 2.599 TFLOPS versus 2.378 TFLOPS, a 9.3% advantage.

Power and physical specs differ sharply. The 870M has a 100 W TDP, is an MXM module, and has no power connectors. The 760 has a 170 W TDP, is dual-slot, requires 2x 6-pin power connectors, and has a 450 W suggested PSU. The 760 also has a defined length of 241 mm (9.5 inches) and specific display outputs, while the 870M's outputs are dependent on the laptop. The 760 has a launch MSRP of 249 USD, while the 870M has no listed MSRP. Release dates differ, with the 760 launching on 2013-06-24 and the 870M on 2014-03-11. Both use the PCIe 3.0 interface, but the 870M uses MXM-B (3.0) while the 760 uses PCIe 3.0 x16.

The Verdict

The data points to a clear winner for raw performance: the GTX 870M. It wins both overlapping benchmarks, has a higher average score, and delivers more FP32 compute and texture throughput. The 61.1% lead in Geekbench Metal is a decisive margin that cannot be ignored. For users running Metal-based applications, the 870M is categorically superior. Even in OpenCL, where the gap narrows to 11.8%, the mobile GPU still comes out ahead.

However, the GTX 760 is not without its strengths. Its 256-bit memory bus provides 192.3 GB/s of bandwidth, a 60% advantage over the 870M. This makes the 760 better suited for bandwidth-sensitive workloads, such as high-resolution textures or certain compute tasks that rely heavily on memory throughput. The 760 also offers more VRAM bandwidth per gigabyte, and its 32 ROPs give it an edge in pixel fill rate at lower resolutions where ROP throughput is the bottleneck.

The choice between these two depends entirely on the platform. The 870M is an MXM module designed for laptops, with a 100 W TDP and no external power connectors. It is the only option for a portable system. The 760 is a dual-slot desktop card requiring a 450 W PSU and 2x 6-pin connectors, making it suitable only for desktop builds. If portability is the requirement, the 870M is the clear pick, offering better benchmark scores in a power-efficient package.

For a desktop user, the 760's higher memory bandwidth and lower price point (launch MSRP of 249 USD) make it an attractive option, despite its lower raw compute. The 760's 2 GB of VRAM may be limiting, but its faster memory speed compensates in many scenarios. Ultimately, the 870M wins on performance metrics, but the 760 wins on memory throughput and desktop compatibility. The data suggests the 870M is the more capable GPU, but the 760 remains a solid choice for desktop users who prioritize bandwidth and don't need the 870M's extra shading units.