NVIDIA GeForce GTX 960 vs NVIDIA GeForce GTX 960M Comparison

The NVIDIA GeForce GTX 960M and the NVIDIA GeForce GTX 960 share a family name, but they are fundamentally different products. The 960M is a mobile part designed for laptops, while the 960 is a desktop card. The benchmark data shows a clear performance gap, with the desktop GTX 960 winning both head-to-head tests. This analysis breaks down where each GPU excels, the architectural reasons for the divide, and which type of user should target which card.

Where Each One Wins

Based on the benchmark results, the desktop NVIDIA GeForce GTX 960 wins in every direct comparison. The 960M does not secure a single victory in the head-to-head tests. However, the 960M’s advantage lies not in raw performance but in its physical characteristics. As an MXM Module with no power connectors and a 75 W TDP, it is designed for portable systems where space and power are at a premium. The desktop GTX 960, with its Dual-slot design and 1x 6-pin power connector, is a fixed installation component.

The data shows the GTX 960 wins decisively in compute workloads. In Geekbench OpenCL, the desktop card scores 18925, while the mobile chip manages only 11045. This is a 41.6% deficit for the 960M. The margin narrows in Vulkan, where the GTX 960 scores 9231 against the 960M’s 8245, a 10.7% difference. For any application that leverages these APIs, the desktop card is the clear choice. The 960M’s only "win" is situational: it exists as a viable option for a laptop where a desktop card cannot be installed.

Architecture Differences

The architectural gap is substantial. The 960M is built on the GM107 chip using the original Maxwell architecture, while the GTX 960 uses the GM206 chip with the newer Maxwell 2.0 architecture. Both are manufactured on a 28 nm process at TSMC, but the silicon differs greatly. The GM107 chip packs 1,870 million transistors on a 148 mm² die, resulting in a transistor density of 12.6M / mm². The GM206 is much larger, with 2,940 million transistors on a 228 mm² die, and a slightly higher density of 12.9M / mm².

This difference in silicon translates directly into core counts. The 960M has 640 shading units, 40 texture mapping units (TMUs), and 16 raster output units (ROPs). The GTX 960 doubles down on these fundamentals with 1024 shading units, 64 TMUs, and 32 ROPs. Clock speeds are similar, with the 960M boosting to 1176 MHz and the GTX 960 boosting to 1178 MHz, but the desktop card’s extra cores provide a massive throughput advantage. The GTX 960 also supports DirectX 12 (12_1), while the 960M is limited to DirectX 12 (11_0). Both support OpenGL 4.6 and Vulkan 1.4.

Memory configurations also differ. The 960M comes with 4 GB of GDDR5 on a 128-bit bus, yielding 80.19 GB/s of bandwidth. The GTX 960 has only 2 GB of GDDR5, also on a 128-bit bus, but with a higher effective memory clock of 7 Gbps, it achieves 112.2 GB/s of bandwidth. The desktop card trades capacity for speed, which benefits performance in most scenarios. The 960M’s higher capacity is likely a concession for mobile users who cannot upgrade memory later.

Head-to-Head Benchmarks

The Geekbench OpenCL test is where the desktop GTX 960 asserts its dominance. With a score of 18925, it is 71.3% higher than the 960M’s 11045. The deltaPct of -41.6% for the 960M indicates it trails by that margin. This is a decisive victory for the desktop card, reflecting its higher pixel rate (37.70 GPixel/s vs 18.82 GPixel/s), texture rate (75.39 GTexel/s vs 47.04 GTexel/s), and FP32 throughput (2.413 TFLOPS vs 1.505 TFLOPS). The 960M’s lower scores are consistent with its reduced core count and memory bandwidth.

The Vulkan test shows a closer contest, but the GTX 960 still wins. The desktop card scores 9231 against the 960M’s 8245, a 10.7% margin. This smaller gap suggests that Vulkan workloads are less sensitive to the raw compute advantages of the GTX 960, but the desktop part still maintains a lead. The 960M’s average benchmark score across all tests is 9645, while the GTX 960’s is 9273. Interestingly, the mobile chip has a higher average score, but this is skewed by the inclusion of different benchmark suites. The GTX 960 also has a 3DMark Steel Nomad DX12 score of 162, a test the 960M did not run.

The data shows the GTX 960 wins both head-to-head tests, but the margin varies. In OpenCL, the desktop card is nearly 80% faster. In Vulkan, the lead shrinks to just over 10%. This suggests that the 960M is not entirely outclassed in every API, but it is consistently behind. The 960M’s percentile ranking of 46 vs the GTX 960’s 45 indicates they sit at nearly the same level across all GPUs, despite the desktop card’s head-to-head wins.

The Verdict

From the data, the choice is clear for anyone building or upgrading a desktop: the NVIDIA GeForce GTX 960 is the superior performer. It wins both head-to-head benchmarks, offers double the shading units, TMUs, and ROPs, and provides significantly higher bandwidth. The GTX 960’s launch MSRP was 199 USD. Its 120 W TDP requires a 300 W suggested PSU, but that is a reasonable requirement for a desktop system.

The GTX 960M is for a different audience. It is an MXM module with a 75 W TDP and no power connectors, making it suitable only for laptops. While it loses every benchmark comparison, it offers 4 GB of memory, which is double the desktop card’s 2 GB. For a mobile user who needs a dedicated GPU and cannot use a desktop card, the 960M is the only option in this pairing. Its performance is still respectable, as its average benchmark score of 9645 is nearly identical to its nearest rival, the NVIDIA Quadro K5000, which scores 9637.

Strictly from the data, the GTX 960 is the pick for desktop users who want maximum performance. The 960M is the pick for laptop users who prioritize portability and a lower power draw. The 960M’s higher memory capacity may also appeal to users with specific VRAM needs, but the GTX 960’s faster memory and higher compute throughput make it the better choice for gaming and general compute tasks.

FAQ

Q: Which GPU wins in Geekbench OpenCL?

A: The NVIDIA GeForce GTX 960 wins with a score of 18925, while the GTX 960M scores 11045. This is a 41.6% deficit for the 960M.

Q: How much faster is the GTX 960 in Vulkan?

A: The GTX 960 scores 9231 in Geekbench Vulkan, compared to the 960M’s 8245, making it 10.7% faster.

Q: Do both GPUs support the same DirectX version?

A: No. The GTX 960 supports DirectX 12 (12_1), while the 960M is limited to DirectX 12 (11_0).

Q: What is the memory bandwidth difference?

A: The GTX 960 has a bandwidth of 112.2 GB/s, while the 960M has 80.19 GB/s. The desktop card provides 32 GB/s more bandwidth.

Q: Which GPU has more shading units?

A: The GTX 960 has 1024 shading units, while the 960M has 640. The desktop card has 384 more shading units.

Q: What is the TDP of each card?

A: The GTX 960 has a TDP of 120 W and requires a 1x 6-pin power connector. The 960M has a TDP of 75 W and requires no power connectors.

Specification Differences

| Specification | NVIDIA GeForce GTX 960M | NVIDIA GeForce GTX 960 |

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

| Chip | GM107 | GM206 |

| Architecture | Maxwell | Maxwell 2.0 |

| Generation | GeForce 900M | GeForce 900 |

| Process Node | 28 nm | 28 nm |

| Transistors | 1,870 million | 2,940 million |

| Die Size | 148 mm² | 228 mm² |

| Transistor Density | 12.6M / mm² | 12.9M / mm² |

| Base Clock | 1097 MHz | 1127 MHz |

| Boost Clock | 1176 MHz | 1178 MHz |

| Memory Clock | 1253 MHz (5 Gbps effective) | 1753 MHz (7 Gbps effective) |

| Memory Size | 4 GB | 2 GB |

| Memory Type | GDDR5 | GDDR5 |

| Memory Bus Width | 128 bit | 128 bit |

| Memory Bandwidth | 80.19 GB/s | 112.2 GB/s |

| Shading Units | 640 | 1024 |

| TMUs | 40 | 64 |

| ROPs | 16 | 32 |

| Pixel Rate | 18.82 GPixel/s | 37.70 GPixel/s |

| Texture Rate | 47.04 GTexel/s | 75.39 GTexel/s |

| FP32 Performance | 1.505 TFLOPS | 2.413 TFLOPS |

| TDP | 75 W | 120 W |

| Slot Width | MXM Module | Dual-slot |

| Power Connectors | None | 1x 6-pin |

| Suggested PSU | - | 300 W |

| Bus Interface | MXM-B (3.0) | PCIe 3.0 x16 |

| Display Outputs | Portable Device Dependent | 1x DVI, 1x HDMI 2.0, 3x DisplayPort 1.2 |

| DirectX | 12 (11_0) | 12 (12_1) |

| Release Date | 2015-03-12 | 2015-01-21 |

| Launch MSRP | - | 199 USD |