NVIDIA GeForce 940M vs NVIDIA GeForce GTX 760M Comparison

The NVIDIA GeForce 940M and NVIDIA GeForce GTX 760M are two end-of-life mobile graphics processors that, despite coming from different architectural generations, land in nearly the same performance tier. The data shows a split decision across the two available benchmark tests, with each card taking one victory. The 940M, built on Maxwell, wins in OpenCL compute workloads, while the older Kepler-based GTX 760M counters with a win in Vulkan graphics performance. Their average benchmark scores are remarkably close, differing by less than one percent. This makes the choice between them highly dependent on the specific application or API being used.

Where Each One Wins

The performance split between these two mobile GPUs is cleanly divided along benchmark type. The NVIDIA GeForce 940M wins the Geekbench OpenCL test with a score of 6018, against 5604 for the GTX 760M. That is a 7.4% advantage for the Maxwell part, indicating that the 940M has a measurable edge in compute-oriented workloads that leverage OpenCL. This suggests the 940M is the stronger choice for general-purpose GPU compute tasks, such as video encoding, physics simulations, or data-parallel processing that can utilize OpenCL.

The NVIDIA GeForce GTX 760M takes the Geekbench Vulkan test with a score of 4868, compared to 4549 for the 940M. This represents a 6.6% lead for the Kepler card, flipping the script in the graphics API arena. Vulkan is a low-overhead graphics API, and the GTX 760M's superior texture and shading resources likely contribute to this win. For modern gaming or graphics applications that run on Vulkan, the GTX 760M holds the advantage. The overall win count is one apiece, confirming a balanced head-to-head matchup where the winner is determined by the API in question rather than overall superiority.

Architecture Differences

The two GPUs represent distinct design philosophies from NVIDIA. The 940M is built on the Maxwell architecture using the GM107 chip, while the GTX 760M is based on the older Kepler architecture with the GK106S chip. Both are manufactured on a 28 nm process at TSMC, which is where the similarities in fabrication end. The GTX 760M has a larger physical footprint, with a die size of 221 mm² and 2,540 million transistors, compared to the 940M's 148 mm² die and 1,870 million transistors. This makes the Kepler chip larger and denser in absolute terms, though the 940M has a higher transistor density at 12.6M / mm² versus 11.5M / mm² for the GTX 760M.

The architectural differences manifest directly in the core configurations. The GTX 760M fields 768 shading units, 64 texture mapping units, and 16 ROPs. The 940M has fewer shading units at 512, and only 32 TMUs, but it also has 16 ROPs. Clock speeds tell the rest of the story: the 940M runs at a base of 1020 MHz and a boost of 1098 MHz, while the GTX 760M runs significantly lower at 628 MHz base and 719 MHz boost. The Maxwell architecture's efficiency allows the 940M to hit much higher clocks, while Kepler relies on a wider execution engine to deliver comparable throughput. The FP32 compute output is nearly identical, with the 940M at 1,124.4 GFLOPS and the GTX 760M at 1,104.4 GFLOPS. However, the texture rate favors the GTX 760M at 46.02 GTexel/s versus 35.14 GTexel/s, and the pixel rate favors the 940M at 17.57 GPixel/s versus 11.50 GPixel/s.

Memory configurations are a major differentiator. The 940M uses 2 GB of DDR3 memory on a 64-bit bus, yielding a bandwidth of 14.40 GB/s. The GTX 760M uses 2 GB of GDDR5 memory on a 128-bit bus, delivering a much higher 64.13 GB/s of bandwidth. This is a 4.5x difference in memory bandwidth in favor of the GTX 760M, which partially explains its Vulkan performance advantage despite lower clocks. The power profiles also differ: the 940M has a TDP of 75 W, while the GTX 760M is rated at 55 W, making the Kepler part more power-efficient despite its larger die. Both cards use an MXM module slot, but the 940M uses an MXM-B (3.0) interface while the GTX 760M uses PCIe 3.0 x16.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce 940M has a slightly higher average benchmark score of 5284, compared to 5236 for the GTX 760M. This is a difference of 0.9%, placing the 940M as the nominal leader in overall performance.

Q: How do the two GPUs compare in memory bandwidth?

A: The GTX 760M has a decisive advantage in memory bandwidth. It features a 128-bit bus with GDDR5 memory providing 64.13 GB/s, while the 940M uses a 64-bit bus with DDR3 memory at 14.40 GB/s. The GTX 760M has over 4x the memory bandwidth.

Q: Which GPU is better for compute workloads?

A: The 940M is better for compute workloads based on the OpenCL benchmark. It scores 6018 in Geekbench OpenCL, which is 7.4% higher than the GTX 760M's 5604. This suggests Maxwell's architecture is more efficient for general compute tasks.

Q: Which GPU offers better Vulkan graphics performance?

A: The GTX 760M offers better Vulkan performance. It scores 4868 in Geekbench Vulkan, which is 6.6% higher than the 940M's 4549. This makes the older Kepler card the better choice for Vulkan-based games and applications.

Q: What are the transistor and die size differences?

A: The GTX 760M has a larger chip with 2,540 million transistors on a 221 mm² die. The 940M has 1,870 million transistors on a 148 mm² die. Despite being smaller, the 940M has a higher transistor density at 12.6M / mm².

Q: Do both GPUs support DirectX 12?

A: Yes, both GPUs support DirectX 12 (11_0). They also both support OpenGL 4.6. The main API difference is in Vulkan support, where the 940M supports version 1.4 and the GTX 760M supports version 1.2.175.

Specification Differences

The key specification differences between the two GPUs are substantial. The 940M uses the GM107 chip on Maxwell architecture, while the GTX 760M uses the GK106S chip on Kepler architecture. The process node is the same at 28 nm, but the transistor counts differ: 1,870 million for the 940M versus 2,540 million for the GTX 760M. The die size also differs, with the 940M at 148 mm² and the GTX 760M at 221 mm². Clock speeds are significantly higher on the 940M, which boosts to 1098 MHz, versus 719 MHz for the GTX 760M.

Memory is a major point of divergence. The 940M has 2 GB of DDR3 on a 64-bit bus with 14.40 GB/s bandwidth. The GTX 760M has 2 GB of GDDR5 on a 128-bit bus with 64.13 GB/s bandwidth. Core counts differ as well: the 940M has 512 shading units and 32 TMUs, while the GTX 760M has 768 shading units and 64 TMUs. Both have 16 ROPs. The pixel rate is higher on the 940M at 17.57 GPixel/s versus 11.50 GPixel/s, but the texture rate is higher on the GTX 760M at 46.02 GTexel/s versus 35.14 GTexel/s. FP32 compute is nearly identical at 1,124.4 GFLOPS for the 940M and 1,104.4 GFLOPS for the GTX 760M.

Power and interface also differ. The 940M has a TDP of 75 W, while the GTX 760M is rated at 55 W. The bus interface is MXM-B (3.0) on the 940M and PCIe 3.0 x16 on the GTX 760M. Both are MXM modules with no power connectors. The release dates are different, with the 940M launching in March 2015 and the GTX 760M in May 2013. The 940M's predecessor is the GeForce 800M, while the GTX 760M's predecessor is the GeForce 600M. The successor generations also differ, with the 940M leading to GeForce 10 Mobile and the GTX 760M leading to GeForce 800M.

Head-to-Head Benchmarks

The head-to-head benchmark data provides a clear, if split, picture. In the Geekbench OpenCL test, the 940M wins decisively with a score of 6018 against 5604 for the GTX 760M. The delta is 7.4% in favor of the 940M. This is the larger margin of victory in either test, suggesting that the 940M's higher clock speeds and Maxwell architecture provide a meaningful compute advantage. The 940M's pixel rate of 17.57 GPixel/s versus 11.50 GPixel/s for the GTX 760M may contribute to this, as compute workloads often benefit from higher fill rates.

In the Geekbench Vulkan test, the GTX 760M reverses the result, scoring 4868 against 4549 for the 940M. The delta is 6.6% in favor of the GTX 760M. This win is likely driven by the GTX 760M's massive memory bandwidth advantage (64.13 GB/s versus 14.40 GB/s) and its higher texture rate (46.02 GTexel/s versus 35.14 GTexel/s). Vulkan workloads often stress memory bandwidth and texture fetching, areas where the Kepler card is clearly superior. The GTX 760M also has more shading units (768 versus 512), which can help in shader-heavy graphics tasks.

The average benchmark scores reflect this balance. The 940M averages 5284 across both tests, while the GTX 760M averages 5236. The delta between them is 0.9%, which is within the margin of error for most benchmarking. In the nearest rivals list, the 940M's average score places it just 0.4% behind the GTX 980M and 0.6% behind the GeForce 930A, while sitting 0.7% ahead of the GeForce 840M. The GTX 760M, for its part, is 0.5% ahead of the Quadro 4000M and 1.5% ahead of the AMD Radeon R7 M260X. Both cards sit at the 31st percentile of all GPUs, confirming their equivalent standing in the broader performance hierarchy.

The Verdict

The data presents a choice between two evenly matched mobile GPUs with different strengths. The NVIDIA GeForce 940M is the pick for users who prioritize OpenCL compute performance. Its 7.4% lead in the OpenCL benchmark and higher pixel rate make it suitable for compute-heavy applications that leverage this API. It also has a marginally higher average benchmark score and a more modern architecture with higher clock speeds, which may offer better responsiveness in general tasks.

The NVIDIA GeForce GTX 760M is the pick for users who prioritize Vulkan graphics performance. Its 6.6% lead in the Vulkan benchmark, backed by superior memory bandwidth and texture rate, makes it the better option for Vulkan-based games and applications. Its lower TDP of 55 W versus 75 W also makes it a more power-efficient choice for laptops where battery life is a concern.

For a user deciding between these two, the decision hinges on the software they intend to run. If the primary use case involves OpenCL compute, the 940M is the clear winner. If the primary use case involves Vulkan gaming, the GTX 760M is the better choice. For a mixed workload, the 940M's higher average score of 5284 versus 5236 gives it a slight edge, but the difference is so small that it should not be the deciding factor. The real tiebreaker is the API support in the target applications. Both cards are end-of-life, so availability and driver support in specific systems will likely dictate the practical choice. The data, however, shows a true split decision with no universal winner.