NVIDIA GeForce GTX 1660 vs NVIDIA GeForce GTX 950A Comparison

Head-to-Head Benchmarks

The recorded data contains a single shared benchmark between these two cards: Geekbench OpenCL. In that test, the NVIDIA GeForce GTX 1660 scores 47,850 points, while the NVIDIA GeForce GTX 950A scores 10,273 points. This represents a delta of 365.8%, meaning the GTX 1660 is roughly four and a half times faster in raw compute throughput as measured by this workload. That is not a marginal improvement; it is a generational leap. The GTX 950A’s sole recorded score places it in the 48th percentile of all GPUs in the database, whereas the GTX 1660 sits at the 51st percentile.

The GTX 1660’s average benchmark score across all recorded tests is 11,680. Its nearest rivals in the database include the AMD Radeon RX 7800 XT with an average score of 11,627 and a delta of 0.5%, meaning the GTX 1660 is effectively tied with that card in overall average performance. It is also 1.3% ahead of the AMD Radeon Pro 5500M and 1.8% ahead of the NVIDIA Tesla K20c. Against the AMD Radeon RX 6500 XT, the GTX 1660 trails by 1.4%. These narrow deltas indicate that the GTX 1660 occupies a stable mid-range performance band, not a top-tier slot.

The GTX 950A’s average benchmark score is 10,273, and its nearest rivals bracket it tightly. The AMD Radeon RX 6500M is 0.9% ahead, the NVIDIA Tesla C2075 is 1.2% ahead, and the AMD Radeon RX 550X is 2% ahead. The only card it beats in its immediate neighborhood is the AMD Radeon R9 M375, which it outperforms by 2%. These figures place the GTX 950A at the lower edge of the database’s performance distribution, consistent with its 48th percentile ranking.

In the single head-to-head test, the GTX 1660 wins outright with a 365.8% advantage. There are no benchmark results where the GTX 950A comes out ahead. The wins tally is 1 for the GTX 1660 and 0 for the GTX 950A. This is a one-sided comparison, but the magnitude of the gap is the story. A 365.8% delta in OpenCL compute is not explainable by clock speed alone; it reflects fundamental architectural and memory differences that are detailed in the next section.

Architecture Differences

The two cards come from entirely different design eras. The GTX 1660 uses the TU116 chip built on Turing architecture, fabricated on a 12 nm process at TSMC. The GTX 950A uses the GM107 chip built on Maxwell architecture, also from TSMC but on a 28 nm process. The process node difference alone, 12 nm versus 28 nm, explains much of the efficiency and density gap. The GTX 1660 packs 6,600 million transistors into a 284 mm² die, yielding a transistor density of 23.2 million per square millimeter. The GTX 950A contains 1,870 million transistors on a 148 mm² die, with a density of 12.6 million per square millimeter. The GTX 1660 has over three times the transistor count and nearly double the die area.

The compute resources are similarly mismatched. The GTX 1660 has 1,408 shading units, 88 texture mapping units, and 48 raster output pipelines. The GTX 950A has 640 shading units, 40 TMUs, and 16 ROPs. That is more than double the shading units, more than double the TMUs, and triple the ROPs. The pixel rate tells the same story: the GTX 1660 achieves 85.68 GPixel/s versus 17.98 GPixel/s for the GTX 950A. Texture rate is 157.1 GTexel/s versus 44.96 GTexel/s. Floating point performance is listed as 5.027 TFLOPS for the GTX 1660 and 1,438.7 GFLOPS (approximately 1.44 TFLOPS) for the GTX 950A, a ratio of roughly 3.5 to 1.

Memory architecture is where the gap becomes even more pronounced. The GTX 1660 uses 6 GB of GDDR5 on a 192-bit bus, delivering 192.1 GB/s of bandwidth. The GTX 950A uses 2 GB of DDR3 on a 128-bit bus, delivering only 32.03 GB/s. That is a sixfold difference in memory bandwidth, which heavily impacts texture-heavy and compute-heavy workloads. The GTX 1660’s memory clock is listed at 2001 MHz with 8 Gbps effective, while the GTX 950A operates at 1001 MHz with 2 Gbps effective. The GTX 1660 also runs at higher core clocks: 1530 MHz base and 1785 MHz boost, versus 993 MHz base and 1124 MHz boost for the GTX 950A.

Both cards support DirectX 12, OpenGL 4.6, and Vulkan 1.4, but the feature levels differ. The GTX 1660 supports DirectX 12 (12_1), while the GTX 950A is limited to DirectX 12 (11_0). That means the GTX 1660 can handle more advanced DX12 features such as conservative rasterization and rasterizer ordered views. Neither card has ray tracing cores or tensor cores, so those are not differentiators here. The GTX 1660 does have a 2:1 FP16 rate of 10.05 TFLOPS, while the GTX 950A lists no FP16 capability at all.

Power and physical characteristics also differ. The GTX 1660 has a TDP of 120 W and requires a single 8-pin power connector, with a suggested power supply of 300 W. The GTX 950A has a TDP of 75 W and uses no power connectors, drawing entirely from its MXM module slot. The GTX 1660 is a dual-slot PCIe 3.0 x16 card with 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a outputs. The GTX 950A is an MXM-B (3.0) module with display outputs described as portable device dependent. The GTX 1660 measures 229 mm in length, 111 mm in height, and 35 mm in width; the GTX 950A has no listed dimensions.

Where Each One Wins

The GTX 1660 wins in every measurable category. In compute workloads, the OpenCL result is 365.8% higher, which translates to faster physics simulations, video encoding, and general GPU compute tasks. The sixfold memory bandwidth advantage makes it far more capable in texture-heavy games and high-resolution rendering. The 6 GB frame buffer versus 2 GB means the GTX 1660 can handle modern game assets and larger working sets without spilling to system memory. The higher pixel rate and texture rate directly improve fill-rate-bound scenarios like shadow mapping and post-processing effects.

For gaming, the GTX 1660 is the clear choice for any title that uses DirectX 12 features at the 12_1 level. The GTX 950A’s 11_0 support limits its compatibility with certain modern rendering paths. The GTX 1660’s boost clock of 1785 MHz versus 1124 MHz provides a substantial raw frequency advantage, and the 2:1 FP16 capability gives it headroom in applications that can use half-precision math. The GTX 950A has no FP16 path, so any workload that could benefit from it will simply run at FP32 speed.

The GTX 950A does have one niche: power-constrained, portable environments. Its 75 W TDP with no external power connector makes it suitable for MXM-based laptops and compact systems where the GTX 1660’s 120 W TDP and 8-pin connector would be impractical. It is also a smaller die at 148 mm², which is relevant for thermal design in tight chassis. However, the performance penalty is severe. The GTX 950A trails the GTX 1660 by 365.8% in the only direct comparison, and its average score of 10,273 is only 88% of the GTX 1660’s average of 11,680, though that average includes different test suites.

In terms of longevity and compatibility, the GTX 1660 is the safer bet. It has a successor in the GeForce 20 series, while the GTX 950A has no listed successor. The GTX 1660’s predecessor is GeForce 10, and its release date is March 2019. The GTX 950A’s predecessor is GeForce 800A, and it launched in March 2015. Both are end-of-life, but the GTX 1660 is four years newer and built on a much more modern process. For any user who needs performance, the GTX 1660 wins outright. For a user who needs a low-power MXM module, the GTX 950A exists, but it does not compete on performance.

FAQ

Q: How much faster is the GTX 1660 than the GTX 950A in OpenCL?

A: The GTX 1660 scores 47,850 points versus 10,273 points for the GTX 950A, a delta of 365.8%. This is the only benchmark shared between the two cards.

Q: What are the memory differences between the two cards?

A: The GTX 1660 has 6 GB of GDDR5 on a 192-bit bus with 192.1 GB/s bandwidth. The GTX 950A has 2 GB of DDR3 on a 128-bit bus with 32.03 GB/s bandwidth.

Q: Which card has a higher pixel fill rate?

A: The GTX 1660 achieves 85.68 GPixel/s, while the GTX 950A achieves 17.98 GPixel/s. The GTX 1660 is nearly five times faster in pixel throughput.

Q: Do both cards support DirectX 12?

A: Both support DirectX 12, but at different feature levels. The GTX 1660 supports DirectX 12 (12_1), while the GTX 950A supports DirectX 12 (11_0).

Q: Which card has a lower power draw?

A: The GTX 950A has a TDP of 75 W and no power connectors. The GTX 1660 has a TDP of 120 W and requires a single 8-pin connector with a suggested 300 W power supply.

Q: What is the GTX 1660’s average benchmark score and percentile?

A: The GTX 1660 has an average benchmark score of 11,680 and sits in the 51st percentile of all GPUs. The GTX 950A has an average score of 10,273 and sits in the 48th percentile.

Specification Differences

The two cards differ on nearly every specification field. The GTX 1660 uses the TU116 chip on a 12 nm process, while the GTX 950A uses the GM107 chip on a 28 nm process. Transistor count is 6,600 million versus 1,870 million. Die size is 284 mm² versus 148 mm². Transistor density is 23.2M per mm² versus 12.6M per mm². Base clock is 1530 MHz versus 993 MHz. Boost clock is 1785 MHz versus 1124 MHz. Memory clock is 2001 MHz with 8 Gbps effective versus 1001 MHz with 2 Gbps effective. Memory size is 6 GB versus 2 GB. Memory type is GDDR5 versus DDR3. Bus width is 192 bit versus 128 bit. Bandwidth is 192.1 GB/s versus 32.03 GB/s. Shading units are 1408 versus 640. TMUs are 88 versus 40. ROPs are 48 versus 16. Pixel rate is 85.68 GPixel/s versus 17.98 GPixel/s. Texture rate is 157.1 GTexel/s versus 44.96 GTexel/s. FP32 performance is 5.027 TFLOPS versus 1,438.7 GFLOPS. FP16 is 10.05 TFLOPS (2:1) for the GTX 1660, while the GTX 950A lists none. TDP is 120 W versus 75 W. Slot width is dual-slot versus MXM module. Power connector is 1x 8-pin versus none. Bus interface is PCIe 3.0 x16 versus MXM-B (3.0). Display outputs are 1x DVI, 1x HDMI 2.0, 1x DisplayPort 1.4a versus portable device dependent. The GTX 1660 has dimensions of 229 mm by 111 mm by 35 mm; the GTX 950A has none listed. DirectX support is 12 (12_1) versus 12 (11_0). Both support OpenGL 4.6 and Vulkan 1.4. The GTX 1660’s launch MSRP is 219 USD; the GTX 950A has no launch MSRP recorded.