NVIDIA GeForce GTX 590 vs NVIDIA GeForce GTX 960A Comparison

NVIDIA GeForce GTX 590 and NVIDIA GeForce GTX 960A represent two distinct approaches to GPU design from the same manufacturer, separated by four years of architectural evolution. The GTX 590 is a dual-GPU flagship from the GeForce 500 generation, built on the Fermi 2.0 architecture at 40 nm, while the GTX 960A is a mobile-oriented MXM module from the GeForce 900A generation, using the Maxwell architecture at 28 nm. Their benchmark results place them within a narrow performance band, with the older card holding a slight edge in the available OpenCL test.

Head-to-Head Benchmarks

The only direct benchmark comparison available is the Geekbench OpenCL test, where the NVIDIA GeForce GTX 590 scores 12830 points against the GTX 960A's 11998 points. This yields a 6.9% advantage for the GTX 590, making it the clear winner in this single head-to-head matchup. The delta is modest but consistent—neither card dominates the other by a wide margin in this compute-oriented workload.

Looking at the broader competitive landscape, the GTX 590's score of 12830 places it nearly exactly at parity with the AMD Radeon Pro 455, which averages 12831 points (0% delta). It edges out the AMD FirePro W5100 by 0.1% (12847 vs 12830) and trails the AMD Radeon 740M by 0.3% (12870 vs 12830). Against its own stablemate, the NVIDIA GeForce GTX 670 scores 12773, putting the GTX 590 0.4% ahead. These are razor-thin margins, indicating the GTX 590 sits in a tightly contested performance tier.

The GTX 960A, with its 11998 score, finds itself in a different competitive neighborhood. It leads the NVIDIA GeForce GTX 1080 by 0.3% (11960 vs 11998), a surprising result given the GTX 1080's later release and higher-tier positioning. The AMD Radeon RX 6500 XT trails by 1.3% (11842), the NVIDIA GeForce GTX 1660 by 2.7% (11680), and the AMD Radeon RX 7800 XT by 3.2% (11627). This clustering suggests the GTX 960A outperforms several modern desktop GPUs in this specific OpenCL benchmark, despite its mobile-oriented design.

When comparing the two cards directly through their nearest rivals, the GTX 590's rivals all score within 0.4% of it, while the GTX 960A's rivals span a wider 3.2% range. This indicates the GTX 590 is more tightly surrounded by comparable performers, whereas the GTX 960A has a clearer separation from its nearest competitors. The 6.9% head-to-head delta between the two cards is larger than any gap seen in their respective rival clusters, reinforcing that the GTX 590 holds a genuine, if modest, performance lead.

The Verdict

The data points to the NVIDIA GeForce GTX 590 as the faster card in raw compute performance, winning the only available benchmark by 6.9%. Its 12830 OpenCL score exceeds the GTX 960A's 11998 by 832 points, a meaningful gap in a benchmark where rival cards are often separated by less than 1%. Anyone prioritizing maximum OpenCL throughput from these two options should choose the GTX 590.

However, the GTX 960A is not without its own merits. Its 51st percentile ranking versus all GPUs is only one point below the GTX 590's 52nd percentile, meaning both cards sit near the median of all GPUs ever tested. The GTX 960A's lead over the GTX 1080, RX 6500 XT, GTX 1660, and RX 7800 XT—all newer or higher-tier parts—shows it punches above its weight class in this workload. For scenarios where the GTX 590's dual-slot, 365 W design is impractical, the GTX 960A's 75 W MXM module offers a dramatically more power-efficient path to comparable performance.

The verdict depends on context. For desktop compute where power and space are not constraints, the GTX 590's higher score makes it the straightforward pick. For mobile or compact systems where the GTX 960A's MXM form factor and minimal power draw are essential, the modest 6.9% performance deficit is an acceptable trade-off. Neither card is a clear winner across all use cases; the GTX 590 wins on raw performance, while the GTX 960A wins on efficiency and form factor suitability.

Where Each One Wins

The GTX 590 wins in raw OpenCL compute performance, as evidenced by its 12830 score versus 11998. It also holds advantages in memory bandwidth (164.0 GB/s vs 80.19 GB/s), pixel rate (19.46 GPixel/s vs 18.82 GPixel/s), and texture rate (38.91 GTexel/s vs 47.04 GTexel/s—though this last figure actually favors the GTX 960A). The GTX 590's 384-bit memory bus versus the GTX 960A's 128-bit bus explains its bandwidth advantage, which can matter in memory-intensive workloads.

The GTX 960A wins in every efficiency-related metric. Its 75 W TDP is dramatically lower than the GTX 590's 365 W, a fivefold difference. It requires no external power connectors, while the GTX 590 needs 2x 8-pin connectors and a 750 W suggested PSU. The GTX 960A's 28 nm process node and 12.6M transistors per mm² density (versus 5.8M on 40 nm) contribute to its efficiency. It also supports Vulkan 1.4, whereas the GTX 590 lists no Vulkan support, and its base clock of 1097 MHz with boost to 1176 MHz provides a defined frequency profile that the GTX 590 lacks entirely.

In terms of memory capacity, the GTX 960A's 2 GB exceeds the GTX 590's 1536 MB, which could benefit workloads with larger working sets. The GTX 960A also has more shading units (640 vs 512) and a higher FP32 throughput (1.505 TFLOPS vs 1,244.2 GFLOPS), yet it still loses the OpenCL benchmark—suggesting the GTX 590's other architectural strengths compensate for its lower shader count and compute rating.

FAQ

Q: Which card has the higher OpenCL benchmark score?

A: The NVIDIA GeForce GTX 590 scores 12830, which is 6.9% higher than the GTX 960A's 11998.

Q: How does the GTX 590 compare to its nearest rivals?

A: The GTX 590 is at parity with the AMD Radeon Pro 455 (12831, 0% delta), 0.1% behind the AMD FirePro W5100 (12847), 0.3% behind the AMD Radeon 740M (12870), and 0.4% ahead of the NVIDIA GeForce GTX 670 (12773).

Q: What rivals does the GTX 960A outperform?

A: The GTX 960A leads the NVIDIA GeForce GTX 1080 by 0.3% (11960), the AMD Radeon RX 6500 XT by 1.3% (11842), the NVIDIA GeForce GTX 1660 by 2.7% (11680), and the AMD Radeon RX 7800 XT by 3.2% (11627).

Q: What is the power consumption difference?

A: The GTX 590 has a 365 W TDP, while the GTX 960A has a 75 W TDP, making the GTX 960A significantly more power-efficient.

Q: Which card supports Vulkan?

A: The GTX 960A lists Vulkan 1.4 support, while the GTX 590's API list includes DirectX 12 (11_0) and OpenGL 4.6 but no Vulkan version.

Q: What are the memory capacities?

A: The GTX 590 has 1536 MB of GDDR5 on a 384-bit bus, while the GTX 960A has 2 GB of GDDR5 on a 128-bit bus.

Architecture Differences

The GTX 590 uses the GF110 chip based on the Fermi 2.0 architecture, fabricated on a 40 nm process at TSMC. It packs 3,000 million transistors into a 520 mm² die, yielding a transistor density of 5.8M per mm². The GTX 960A uses the GM107 chip based on the Maxwell architecture, also from TSMC but on a 28 nm process. It contains 1,870 million transistors on a 148 mm² die, achieving a much higher density of 12.6M per mm². This density improvement reflects the architectural advancements between Fermi and Maxwell.

The GTX 590's Fermi 2.0 design features 512 shading units, 64 TMUs, and 48 ROPs. Its memory subsystem includes 1536 MB of GDDR5 on a 384-bit bus, delivering 164.0 GB/s of bandwidth. The GTX 960A's Maxwell design has 640 shading units, 40 TMUs, and 16 ROPs, with 2 GB of GDDR5 on a 128-bit bus providing 80.19 GB/s. Despite fewer TMUs and ROPs, the GTX 960A achieves a higher texture rate (47.04 GTexel/s vs 38.91 GTexel/s) thanks to its higher clock speeds.

Both cards support DirectX 12 (11_0) and OpenGL 4.6, but the GTX 960A adds Vulkan 1.4 support, which the GTX 590 lacks. The GTX 590's pixel rate of 19.46 GPixel/s slightly exceeds the GTX 960A's 18.82 GPixel/s, while the GTX 960A's FP32 throughput of 1.505 TFLOPS surpasses the GTX 590's 1,244.2 GFLOPS. Neither card includes ray tracing cores or tensor cores, as both predate those features.

Specification Differences

The two cards differ across nearly every specification category. The GTX 590 uses a 40 nm process node, while the GTX 960A uses 28 nm. The GTX 590's die size is 520 mm² versus 148 mm² for the GTX 960A, and its transistor count is 3,000 million versus 1,870 million. Transistor density favors the GTX 960A at 12.6M/mm² compared to 5.8M/mm².

Clock speeds show the GTX 960A with a base clock of 1097 MHz and boost clock of 1176 MHz, while the GTX 590 lists no base or boost clocks. Memory clocks differ: the GTX 590 runs at 854 MHz (3.4 Gbps effective), and the GTX 960A at 1253 MHz (5 Gbps effective). The GTX 590 has 1536 MB of memory, the GTX 960A has 2 GB. Bus width is 384-bit versus 128-bit, and bandwidth is 164.0 GB/s versus 80.19 GB/s.

Shading units, TMUs, and ROPs all differ: 512/64/48 for the GTX 590 versus 640/40/16 for the GTX 960A. Pixel rate is 19.46 GPixel/s versus 18.82 GPixel/s, but texture rate favors the GTX 960A at 47.04 GTexel/s versus 38.91 GTexel/s. FP32 compute is 1,244.2 GFLOPS versus 1.505 TFLOPS. Power draw is 365 W versus 75 W, with the GTX 590 requiring 2x 8-pin connectors and a 750 W suggested PSU, while the GTX 960A needs no external power and lists no PSU suggestion. The GTX 590 is a dual-slot card measuring 279 mm x 111 mm x 40 mm, while the GTX 960A is an MXM Module with no listed dimensions. Bus interface is PCIe 2.0 x16 for the GTX 590 and MXM-B (3.0) for the GTX 960A. Display outputs are 3x DVI and 1x mini-DisplayPort for the GTX 590, versus "Portable Device Dependent" for the GTX 960A. The GTX 590 launched with a 699 USD MSRP; the GTX 960A has no listed launch MSRP.