NVIDIA GeForce GTX 950 vs NVIDIA GeForce GTX 960A Comparison

# NVIDIA GeForce GTX 960A vs NVIDIA GeForce GTX 950

The NVIDIA GeForce GTX 960A and NVIDIA GeForce GTX 950 are both end-of-life Maxwell-generation graphics cards from NVIDIA, but they serve very different purposes. The GTX 960A is a mobile-oriented MXM module built on the GM107 chip, while the GTX 950 is a desktop dual-slot card using the GM206 chip. Benchmark data shows the GTX 950 holds a commanding lead in OpenCL performance, scoring 15,662 versus the GTX 960A's 11,998 — a 23.4% advantage. The GTX 950 also ranks higher overall, sitting in the 53rd percentile of all GPUs compared to the GTX 960A's 51st percentile. However, the comparison is not simply about raw speed; the two cards target different physical environments and feature sets that may matter more than benchmark scores alone.

FAQ

Q: Which GPU has the higher OpenCL benchmark score?

A: The NVIDIA GeForce GTX 950 scores 15,662 in Geekbench OpenCL, while the GTX 960A scores 11,998. This gives the GTX 950 a 23.4% advantage in this specific test.

Q: How do the two cards compare in overall GPU percentile ranking?

A: The GTX 950 ranks in the 53rd percentile of all GPUs, while the GTX 960A ranks in the 51st percentile. This indicates the GTX 950 sits slightly higher in the overall performance distribution.

Q: What are the memory bandwidth specifications for each card?

A: The GTX 950 offers 105.8 GB/s of memory bandwidth with 6.6 Gbps effective memory speed, whereas the GTX 960A provides 80.19 GB/s with 5 Gbps effective memory speed. Both use 2 GB of GDDR5 memory on a 128-bit bus.

Q: Do these cards support different DirectX versions?

A: Yes. The GTX 950 supports DirectX 12 (12_1), while the GTX 960A supports DirectX 12 (11_0). This means the GTX 950 has a higher feature level for DirectX 12 applications.

Q: What is the physical form factor difference between the two cards?

A: The GTX 960A uses an MXM Module with an MXM-B (3.0) bus interface and no power connectors, making it suitable for portable devices. The GTX 950 is a dual-slot desktop card with a PCIe 3.0 x16 interface, a 1x 6-pin power connector, and a length of 202 mm (8 inches).

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

A: The GTX 950 has 768 shading units and 48 TMUs, compared to the GTX 960A's 640 shading units and 40 TMUs. The GTX 950 also has double the ROPs, with 32 versus 16.

The Verdict

The data points clearly to the NVIDIA GeForce GTX 950 as the stronger performer in raw compute benchmarks. Its OpenCL score of 15,662 is 23.4% higher than the GTX 960A's 11,998, and its average benchmark score of 13,189 exceeds the GTX 960A's 11,998 by roughly 10%. The GTX 950 also wins in every architectural specification that matters for throughput: more shading units (768 vs 640), more TMUs (48 vs 40), double the ROPs (32 vs 16), higher FP32 performance (1.825 TFLOPS vs 1.505 TFLOPS), and substantially higher memory bandwidth (105.8 GB/s vs 80.19 GB/s).

Picking between these two should come down to the physical deployment scenario. The GTX 960A is an MXM module with no power connectors and portable-device-dependent display outputs, meaning it is built for laptops or compact systems where space and power are constrained. Its 75 W TDP is 15 W lower than the GTX 950's 90 W, and it requires no external power connector. The GTX 950, in contrast, is a desktop card with a 1x 6-pin connector, a 250 W suggested PSU, and a full array of display outputs including DVI, HDMI 2.0, and three DisplayPort 1.2 connections.

For anyone building or upgrading a desktop system, the GTX 950 is the logical choice based on raw benchmark superiority and a richer feature set. For a mobile or embedded application where the MXM form factor is required, the GTX 960A is the only viable option, despite its lower performance. The GTX 950 also holds an edge in API support with DirectX 12 (12_1) versus the GTX 960A's DirectX 12 (11_0), which could affect compatibility with newer titles that leverage higher feature levels.

Head-to-Head Benchmarks

The single head-to-head benchmark available in the data is Geekbench OpenCL, and it decisively favors the GTX 950. The GTX 950 scores 15,662 against the GTX 960A's 11,998, a delta of 23.4%. This is a substantial margin that reflects the underlying hardware differences: the GTX 950's GM206 chip has 2,940 million transistors on a 228 mm² die, while the GTX 960A's GM107 has 1,870 million transistors on a 148 mm² die. The GTX 950's 48 TMUs and 32 ROPs give it higher texture and pixel rates—57.02 GTexel/s and 38.02 GPixel/s respectively, versus the GTX 960A's 47.04 GTexel/s and 18.82 GPixel/s.

The GTX 950's memory subsystem also contributes to its OpenCL advantage. Its memory clock of 1653 MHz (6.6 Gbps effective) yields 105.8 GB/s of bandwidth, a 31.9% improvement over the GTX 960A's 80.19 GB/s. This bandwidth advantage is critical for compute workloads that frequently access large data sets, and it explains why the GTX 950 outperforms despite the GTX 960A having a higher base clock (1097 MHz vs 1024 MHz). The boost clocks are closer—1176 MHz for the GTX 960A versus 1188 MHz for the GTX 950—but the GTX 950's additional execution resources and memory throughput dominate the comparison.

Notably, the GTX 950 has additional benchmark scores in Geekbench Metal (7,172) and Geekbench Vulkan (16,734), while the GTX 960A only has OpenCL results. This suggests the GTX 950 has broader API support in the benchmarking suite, though the DirectX 12 (12_1) versus (11_0) difference also indicates a higher feature level.

Specification Differences

The two cards diverge significantly across almost every measurable specification. The GTX 960A uses the GM107 chip from the Maxwell architecture, while the GTX 950 uses the GM206 chip from Maxwell 2.0. The GTX 960A belongs to the GeForce 900A generation, whereas the GTX 950 is part of the GeForce 900 generation. Transistor counts differ substantially: 1,870 million for the GTX 960A versus 2,940 million for the GTX 950, with die sizes of 148 mm² and 228 mm² respectively. Transistor density is nearly identical at 12.6M/mm² and 12.9M/mm².

Clock speeds show a mixed picture. The GTX 960A has a higher base clock at 1097 MHz versus the GTX 950's 1024 MHz, but the boost clocks are close at 1176 MHz and 1188 MHz. Memory clocks favor the GTX 950 heavily: 1653 MHz (6.6 Gbps effective) versus 1253 MHz (5 Gbps effective). Both cards use 2 GB of GDDR5 on a 128-bit bus, but bandwidth differs by 25.61 GB/s in favor of the GTX 950.

Compute resources are uniformly higher on the GTX 950: 768 shading units (vs 640), 48 TMUs (vs 40), and 32 ROPs (vs 16). Pixel rate is 38.02 GPixel/s versus 18.82 GPixel/s, texture rate is 57.02 GTexel/s versus 47.04 GTexel/s, and FP32 is 1.825 TFLOPS versus 1.505 TFLOPS. Power and physical specifications also differ: the GTX 960A consumes 75 W with no power connectors and an MXM-B (3.0) interface, while the GTX 950 consumes 90 W with a 1x 6-pin connector, a 250 W suggested PSU, and a PCIe 3.0 x16 interface. Display outputs are portable-device-dependent on the GTX 960A, whereas the GTX 950 offers 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.2. The GTX 950 is also 202 mm (8 inches) long and dual-slot.

Architecture Differences

The architectural gap between these two cards stems from their different Maxwell generations. The GTX 960A uses the original Maxwell architecture on the GM107 chip, which was designed for lower-power mobile applications. The GTX 950 uses Maxwell 2.0 on the GM206 chip, which introduced hardware improvements and a higher DirectX feature level (12_1 versus 11_0). This DirectX difference is notable because it affects which rendering features are available in games and applications.

The GM206 chip in the GTX 950 has 57% more transistors (2,940 million vs 1,870 million) and a 54% larger die (228 mm² vs 148 mm²). This additional silicon is dedicated to more shading units, TMUs, and ROPs, as well as a wider memory pipeline that achieves higher effective bandwidth despite the same 128-bit bus width. The GTX 960A's lower transistor count and die size reflect its mobile orientation, where power efficiency and physical footprint take priority over raw throughput.

Both cards are built on the same 28 nm TSMC process and share the same OpenGL (4.6) and Vulkan (1.4) API support. Neither card has ray tracing cores or tensor cores, which is expected given their Maxwell-era design. The GTX 950's successors include GeForce 10 series cards, while the GTX 960A's predecessor is GeForce 800A, indicating the GTX 960A is part of a mobile-specific lineage. The GTX 950's predecessor is GeForce 700, showing its desktop heritage.

Where Each One Wins

The GTX 950 wins decisively in all compute and rendering benchmarks. It is 23.4% faster in OpenCL, has 21.3% higher FP32 throughput (1.825 TFLOPS vs 1.505 TFLOPS), doubles the pixel fill rate (38.02 GPixel/s vs 18.82 GPixel/s), and offers 31.9% more memory bandwidth (105.8 GB/s vs 80.19 GB/s). It also supports DirectX 12 (12_1) versus the GTX 960A's (11_0), which may enable additional rendering features in compatible software. For desktop users who need maximum performance per benchmark score, the GTX 950 is the clear winner.

The GTX 960A wins in the mobile and embedded space by virtue of its MXM form factor. It has a lower TDP of 75 W versus 90 W, requires no external power connector, and is designed for portable devices where the GTX 950's dual-slot 202 mm length and 6-pin connector would be impossible to accommodate. Its higher base clock of 1097 MHz also suggests it can maintain performance in thermally constrained environments, though the boost clock is slightly lower at 1176 MHz versus 1188 MHz.

For users who prioritize benchmark performance in a standard desktop chassis, the GTX 950 is the only sensible choice. For system integrators building compact laptops or specialized equipment that requires an MXM module, the GTX 960A is the designated option, even with its lower scores. The GTX 950 also has a launch MSRP of 159 USD, which is not a factor in this comparison but provides historical context. Ultimately, the data shows the GTX 950 as the superior GPU in every measurable performance category, while the GTX 960A's value lies entirely in its physical compatibility with portable systems.