NVIDIA GeForce GTX 880M vs NVIDIA GeForce GTX 960 Comparison

The NVIDIA GeForce GTX 960 and NVIDIA GeForce GTX 880M represent two distinct design philosophies from the same manufacturer, separated by nearly a year in release timing. The GTX 960 is a desktop-oriented card built on the Maxwell 2.0 architecture, while the GTX 880M is a mobile-focused part using the older Kepler architecture. The database shows the GTX 960 holds a higher average benchmark score of 9273 compared to the GTX 880M’s 8040, a difference of roughly 15% in favor of the newer desktop part. However, the data also reveals that the GTX 880M wins decisively in one specific test, making this comparison less straightforward than a simple aggregate score would suggest. This page explores the architectural split, the benchmark results, and what each card does best according to the recorded measurements.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 960 records an average benchmark score of 9273, while the NVIDIA GeForce GTX 880M records 8040. The GTX 960 sits at the 45th percentile among all GPUs, whereas the GTX 880M sits at the 42nd percentile.

Q: How do the two compare in the Geekbench Metal test?

A: The GTX 880M wins the Geekbench Metal test with a score of 10458, compared to the GTX 960’s 8773. That is a 16.1% advantage for the GTX 880M, according to the head-to-head data.

Q: What about the Geekbench OpenCL test?

A: The GTX 960 dominates the Geekbench OpenCL test, scoring 18925 versus the GTX 880M’s 5622. The head-to-head delta shows a 236.6% lead for the GTX 960, making this the largest performance gap between the two cards.

Q: Which GPU has more shading units and texture mapping units?

A: The GTX 880M has 1536 shading units and 128 texture mapping units. The GTX 960 has 1024 shading units and 64 texture mapping units. Despite having fewer units, the GTX 960 achieves a higher pixel rate of 37.70 GPixel/s versus the GTX 880M’s 31.78 GPixel/s.

Q: What are the memory specifications for each card?

A: The GTX 960 comes with 2 GB of GDDR5 memory on a 128-bit bus, providing 112.2 GB/s of bandwidth. The GTX 880M features 8 GB of GDDR5 memory on a 256-bit bus, delivering 160.0 GB/s of bandwidth.

Q: Which card was released earlier?

A: The GTX 880M was released on March 11, 2014, while the GTX 960 was released on January 21, 2015. The GTX 880M is part of the GeForce 800M generation, and the GTX 960 belongs to the GeForce 900 generation.

Architecture Differences

The two GPUs come from different architectural families. The GTX 960 uses the GM206 chip based on Maxwell 2.0, while the GTX 880M relies on the GK104 chip from the older Kepler architecture. Both are manufactured on the same 28 nm process at TSMC, but that is where the similarities in silicon end. The GTX 880M packs more transistors: 3,540 million compared to the GTX 960’s 2,940 million. The die size also differs, with the GTX 880M measuring 294 mm² and the GTX 960 measuring 228 mm². Interestingly, the GTX 960 has a higher transistor density at 12.9 million per mm² versus the GTX 880M’s 12.0 million per mm², indicating a more compact layout for the newer part.

Clock speeds favor the GTX 960. It runs at a base clock of 1127 MHz and a boost clock of 1178 MHz, while the GTX 880M operates at 954 MHz base and 993 MHz boost. The memory clocks also diverge: the GTX 960’s memory runs at 1753 MHz (7 Gbps effective), whereas the GTX 880M’s memory runs at 1250 MHz (5 Gbps effective). These higher clocks help the GTX 960 overcome the GTX 880M’s raw unit advantage in several workloads.

The feature sets differ in API support too. The GTX 960 supports DirectX 12 (12_1) and Vulkan 1.4, while the GTX 880M supports DirectX 12 (11_0) and Vulkan 1.2.175. Both support OpenGL 4.6. The GTX 960 also has a higher pixel rate of 37.70 GPixel/s, but the GTX 880M has a higher texture rate of 127.1 GTexel/s. Floating-point performance favors the GTX 880M, which delivers 3.050 TFLOPS, while the GTX 960 delivers 2.413 TFLOPS. Neither card has ray tracing cores or tensor cores, and neither lists a separate FP16 performance figure.

Where Each One Wins

The benchmark data paints a split picture. The GTX 880M wins the Geekbench Metal test, scoring 10458 against the GTX 960’s 8773, a 16.1% margin. Metal is Apple’s graphics API, and this result suggests the GTX 880M has an edge in that specific environment, likely due to its higher shading unit count and larger memory bus. For applications that rely heavily on Metal, the GTX 880M appears to be the stronger choice.

The GTX 960, however, wins the Geekbench OpenCL test by a massive margin. Its score of 18925 dwarfs the GTX 880M’s 5622, representing a 236.6% advantage. OpenCL is a cross-platform compute API, and the GTX 960’s newer Maxwell architecture appears to handle these workloads far more efficiently. For compute-heavy tasks, video encoding, or any OpenCL-accelerated application, the GTX 960 is clearly superior.

Beyond these two tests, the GTX 960 also records a Geekbench Vulkan score of 9231 and a 3DMark Steel Nomad DX12 score of 162. The GTX 880M has no recorded scores for those tests, so no direct comparison is possible. The GTX 960’s higher average benchmark score (9273 versus 8040) and its higher percentile rank (45th versus 42nd) indicate that, across the full set of available measurements, the GTX 960 is the more consistent performer.

Specification Differences

The two cards differ in nearly every specification category. The GTX 960 uses the GM206 chip, while the GTX 880M uses the GK104. The GTX 960’s process node is 28 nm at TSMC, matching the GTX 880M, but the transistor counts differ: 2,940 million for the GTX 960 versus 3,540 million for the GTX 880M. The die size is 228 mm² for the GTX 960 and 294 mm² for the GTX 880M.

Clock speeds show the GTX 960 running faster: 1127 MHz base and 1178 MHz boost compared to the GTX 880M’s 954 MHz base and 993 MHz boost. Memory configurations are also different. The GTX 960 has 2 GB of GDDR5 on a 128-bit bus with 112.2 GB/s bandwidth, while the GTX 880M has 8 GB of GDDR5 on a 256-bit bus with 160.0 GB/s bandwidth. The memory clock is 1753 MHz (7 Gbps effective) on the GTX 960 and 1250 MHz (5 Gbps effective) on the GTX 880M.

Compute resources vary. The GTX 880M has more shading units (1536 versus 1024) and more texture mapping units (128 versus 64), but both have 32 ROPs. The GTX 960 achieves a higher pixel rate of 37.70 GPixel/s, while the GTX 880M has a higher texture rate of 127.1 GTexel/s. FP32 performance is higher on the GTX 880M at 3.050 TFLOPS, versus the GTX 960’s 2.413 TFLOPS.

Power and form factor also differ. The GTX 960 has a TDP of 120 W, a dual-slot design, a 1x 6-pin power connector, and a suggested PSU of 300 W. The GTX 880M has a TDP of 122 W, an MXM module form factor, no power connectors, and no suggested PSU listed. The GTX 960 uses a PCIe 3.0 x16 bus interface, while the GTX 880M uses MXM-B (3.0). Display outputs are also distinct: the GTX 960 offers 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.2, whereas the GTX 880M’s outputs are listed as “Portable Device Dependent,” meaning they vary by laptop design.

Head-to-Head Benchmarks

The head-to-head data includes only two tests, and each card wins one. In Geekbench Metal, the GTX 880M scores 10458, beating the GTX 960’s 8773. The percentage difference is 16.1% in favor of the GTX 880M. This is a notable victory for the older Kepler part, especially given that the GTX 960 has higher clock speeds and a newer architecture. The win likely stems from the GTX 880M’s larger memory bandwidth (160.0 GB/s versus 112.2 GB/s) and higher shading unit count, which can benefit certain Metal workloads.

In Geekbench OpenCL, the GTX 960 turns the tables with a score of 18925, compared to the GTX 880M’s 5622. The percentage difference is 236.6%, meaning the GTX 960 delivers more than three times the performance in this test. This is the single largest gap in any comparison between the two cards. The GTX 960’s Maxwell 2.0 architecture appears to handle OpenCL compute far more efficiently, despite having fewer shading units and lower theoretical FP32 throughput.

The aggregate average benchmark score further separates the two. The GTX 960 averages 9273, while the GTX 880M averages 8040. The GTX 960’s nearest rivals include the NVIDIA GeForce GTX 465 (average score 9294, a 0.2% difference) and the NVIDIA GeForce GTX 850M (average score 9302, a 0.3% difference). The GTX 880M’s nearest rivals include the NVIDIA Quadro P5000 (average score 8039, a 0% difference) and the NVIDIA GeForce GTX 650 Ti (average score 8053, a 0.2% difference). These figures place the GTX 960 in a slightly higher performance tier.

The Verdict

The data suggests a clear split in use cases. For users prioritizing Metal-based graphics performance, the GTX 880M is the better choice, as it leads by 16.1% in that specific benchmark. Its 8 GB memory capacity and 256-bit bus also make it attractive for applications that need large frame buffers or high bandwidth, even if the overall compute performance lags.

For most other scenarios, the GTX 960 is the stronger card. Its OpenCL score is 236.6% higher, its average benchmark score is 15.3% higher (9273 versus 8040), and it ranks in the 45th percentile versus the GTX 880M’s 42nd. The GTX 960 also supports newer API features, including DirectX 12 (12_1) and Vulkan 1.4, which may matter for future software compatibility. Its lower memory capacity (2 GB versus 8 GB) and narrower bus (128-bit versus 256-bit) are the main drawbacks, but the recorded performance data shows that the GTX 960 compensates with higher clocks and architectural efficiency.

The GTX 960 is the appropriate pick for desktop users who need strong compute performance, modern API support, and a higher overall benchmark standing. The GTX 880M, being an MXM module for portable devices, is the choice for laptop systems where its larger memory pool and Metal performance are relevant. Neither card is a universal winner, but the GTX 960’s aggregate scores and compute dominance give it the edge in most measured workloads.