NVIDIA GeForce GTX 1070 Ti vs NVIDIA GeForce GTX 965M Comparison

The NVIDIA GeForce GTX 965M and the NVIDIA GeForce GTX 1070 Ti represent two distinct eras of mobile and desktop graphics, yet the benchmark data reveals they are surprisingly close in aggregate performance. The GTX 1070 Ti is the clear winner in every head-to-head test, but both cards sit at the 56th percentile among all GPUs, with the GTX 965M posting an average benchmark score of 14404 against the GTX 1070 Ti’s 14277. This near-identical average score is misleading, as the GTX 1070 Ti’s victories are decisive in raw compute workloads, while the GTX 965M’s closest rivals include the AMD Radeon RX Vega 11 and NVIDIA GeForce GTX TITAN, showing it competes in a different performance class than its desktop counterpart.

Head-to-Head Benchmarks

The data available for direct comparison is limited to two OpenCL and Vulkan tests, and the GTX 1070 Ti dominates both without exception. In the Geekbench OpenCL test, the GTX 1070 Ti scores 49219, while the GTX 965M manages only 14509, resulting in a delta of -70.5% for the older mobile chip. This is not a marginal difference; it is a 3.4x performance gap, indicating that the GTX 1070 Ti’s compute throughput is in an entirely different league, driven by its 2432 shading units and 8.186 TFLOPS FP32 performance.

The Geekbench Vulkan test tells an even more lopsided story. The GTX 1070 Ti scores 61006, compared to the GTX 965M’s 14299, a delta of -76.6%. This 4.3x margin highlights how the Pascal architecture’s superior geometry processing and driver optimization for modern APIs translate into massive gains over Maxwell 2.0. The GTX 965M’s Vulkan score of 14299 is actually slightly lower than its OpenCL score of 14509, suggesting the older architecture does not scale as well with Vulkan’s low-level overhead.

The GTX 1070 Ti’s other benchmarks reinforce its dominance. Its Passmark G3D score is 14674, which is nearly identical to the GTX 965M’s average benchmark score of 14404, but this is misleading because the GTX 1070 Ti’s average is pulled down by outlier tests like Passmark DirectX 9 (207) and Passmark DirectX 10 (90), which are likely running at lower resolutions or with different driver paths. The GTX 1070 Ti also posts a Geekbench Metal score of 22180, a test the GTX 965M does not have data for, further indicating the desktop card’s broader API support and higher peak performance.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The NVIDIA GeForce GTX 965M has an average benchmark score of 14404, which is slightly higher than the NVIDIA GeForce GTX 1070 Ti’s 14277. However, this average is based on different test sets, with the GTX 965M only having two benchmarks (Geekbench OpenCL and Vulkan) while the GTX 1070 Ti has eleven.

Q: How much faster is the GTX 1070 Ti in OpenCL?

A: The GTX 1070 Ti scores 49219 in Geekbench OpenCL, while the GTX 965M scores 14509. This gives the GTX 1070 Ti a 70.5% lead, meaning it is roughly 3.4 times faster in this compute workload.

Q: What is the GTX 965M’s closest rival?

A: The GTX 965M’s nearest rival is the AMD Radeon RX Vega 11, which has an average score of 14385 and a delta of 0.1%. The NVIDIA GeForce GTX TITAN is also close at 14373, with a 0.2% delta.

Q: Does the GTX 1070 Ti have a higher memory bandwidth than the GTX 965M?

A: Yes, the GTX 1070 Ti has a memory bandwidth of 256.3 GB/s, which is over three times higher than the GTX 965M’s 80.19 GB/s. This is due to its 256-bit bus and 8 Gbps effective memory speed versus the GTX 965M’s 128-bit bus and 5 Gbps effective speed.

Q: Are both GPUs end-of-life?

A: Yes, both the GTX 965M and GTX 1070 Ti have a production status of "End-of-life." The GTX 965M was released on 2015-01-08, while the GTX 1070 Ti was released on 2017-11-01.

Q: Which GPU has more shading units?

A: The GTX 1070 Ti has 2432 shading units, while the GTX 965M has 1024. This more than doubling of shading units is a primary driver of the GTX 1070 Ti’s higher FP32 throughput of 8.186 TFLOPS versus 1.946 TFLOPS.

Architecture Differences

The two GPUs are built on fundamentally different architectures and process nodes, explaining their vast performance disparity. The GTX 965M uses the GM204 chip based on Maxwell 2.0 architecture, fabricated on a 28 nm process at TSMC. This older node packs 5,200 million transistors into a 398 mm² die, resulting in a transistor density of 13.1M per mm². In contrast, the GTX 1070 Ti uses the GP104 chip based on Pascal architecture, built on a more advanced 16 nm process, also at TSMC. This smaller node allows 7,200 million transistors in a smaller 314 mm² die, achieving a higher density of 22.9M per mm².

The memory subsystems are equally divergent. The GTX 965M has 2 GB of GDDR5 memory on a 128-bit bus, delivering 80.19 GB/s bandwidth. The GTX 1070 Ti offers 8 GB of GDDR5 on a 256-bit bus, quadrupling the memory capacity and more than tripling the bandwidth to 256.3 GB/s. Clock speeds also favor the newer card: the GTX 1070 Ti runs at a base of 1607 MHz and boost of 1683 MHz, while the GTX 965M is limited to 924 MHz base and 950 MHz boost. This clock advantage, combined with more cores, gives the GTX 1070 Ti a pixel rate of 107.7 GPixel/s and a texture rate of 255.8 GTexel/s, versus 30.40 GPixel/s and 60.80 GTexel/s for the GTX 965M.

The GTX 1070 Ti also supports FP16 compute at 127.9 GFLOPS (1:64 ratio), a feature absent from the GTX 965M’s specifications. Both cards support DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4, but the GTX 1070 Ti’s PCIe 3.0 x16 interface is a desktop standard, while the GTX 965M uses an MXM-B (3.0) module slot, indicating its laptop-oriented design. The GTX 1070 Ti requires a 180 W TDP and a 450 W suggested PSU with a single 8-pin connector, while the GTX 965M has no power connectors and relies on the MXM slot’s power delivery.

The Verdict

The data is unambiguous: the NVIDIA GeForce GTX 1070 Ti is the superior GPU for any workload that demands raw compute or modern API performance. It wins both head-to-head benchmarks with deltas of -70.5% and -76.6%, and its 8.186 TFLOPS FP32 performance dwarfs the GTX 965M’s 1.946 TFLOPS. Any user comparing these two for gaming or content creation should choose the GTX 1070 Ti without hesitation, as it offers over four times the Vulkan performance and over three times the OpenCL performance.

However, the GTX 965M is not without merit in its own context. As a mobile GPU with an MXM form factor and no external power connectors, it is designed for laptops where the GTX 1070 Ti’s 267 mm length, 112 mm height, and dual-slot width would be physically impossible to accommodate. The GTX 965M’s 2 GB memory and 80.19 GB/s bandwidth are sufficient for 1080p gaming at lower settings in its era, and its 56th percentile ranking shows it was a mid-range performer at release. For a system builder with a legacy laptop, the GTX 965M remains a functional option, but for any new build or upgrade, the GTX 1070 Ti is the only rational choice based on performance data alone.

Specification Differences

The key specification differences between the two cards are stark and directly explain their performance gap. The GTX 1070 Ti has 2432 shading units, 152 TMUs, and 64 ROPs, while the GTX 965M has 1024 shading units, 64 TMUs, and 32 ROPs. This means the GTX 1070 Ti has 2.4x the shading units, 2.4x the TMUs, and 2x the ROPs. Clock speeds also differ significantly: the GTX 1070 Ti boosts to 1683 MHz versus the GTX 965M’s 950 MHz, a 77% higher boost clock.

Memory capacity and bandwidth favor the GTX 1070 Ti overwhelmingly. It has 8 GB of GDDR5 on a 256-bit bus with 256.3 GB/s bandwidth, compared to 2 GB on a 128-bit bus with 80.19 GB/s. The GTX 1070 Ti’s FP32 performance of 8.186 TFLOPS is 4.2x higher than the GTX 965M’s 1.946 TFLOPS. Process node is a major differentiator: 16 nm versus 28 nm, leading to a higher transistor density of 22.9M/mm² versus 13.1M/mm² despite a smaller die size (314 mm² vs 398 mm²). The GTX 1070 Ti also has a TDP of 180 W and requires a 450 W PSU, while the GTX 965M has no listed TDP and no power connectors. The GTX 1070 Ti uses PCIe 3.0 x16 and has display outputs of 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.4a, whereas the GTX 965M uses MXM-B (3.0) and has portable device dependent outputs.

Where Each One Wins

The GTX 1070 Ti wins decisively in every measurable benchmark category. Its Geekbench OpenCL score of 49219 versus 14509 makes it the clear choice for compute-heavy applications like GPU rendering, scientific simulations, or machine learning inference. Its Vulkan score of 61006 versus 14299 indicates superior performance in modern games that utilize Vulkan’s low-level API, making it ideal for high-refresh-rate 1440p or 4K gaming. The GTX 1070 Ti’s 8 GB memory capacity is also a significant advantage for texture-heavy workloads and larger datasets, while its 256.3 GB/s bandwidth ensures data can be fed to the 2432 shading units without bottleneck.

The GTX 965M’s advantages are not in performance but in form factor and power efficiency. As an MXM module with no power connectors, it is the only option for thin-and-light laptops or existing MXM-based systems. Its 2 GB memory and 80.19 GB/s bandwidth are adequate for older games or less demanding applications at 720p or 1080p with reduced settings. The GTX 965M’s 28 nm process and lower transistor count (5,200 million) mean it generates less heat, which is critical in a constrained laptop chassis. For users who prioritize portability over frame rates, the GTX 965M remains a viable choice, but it wins no performance benchmarks against the GTX 1070 Ti. The GTX 1070 Ti is the winner for anyone who can accommodate its size and power requirements.