NVIDIA GeForce GTX 590 vs NVIDIA GeForce MX350 Comparison

Head-to-Head Benchmarks

The only direct benchmark comparison recorded in the database is the Geekbench OpenCL test, and the results are decisive. The NVIDIA GeForce GTX 590 scores 12,830, while the NVIDIA GeForce MX350 scores 8,689. That gives the GTX 590 a 47.7% lead, a substantial margin that reflects the fundamental performance gap between the two generations and market segments.

Looking at the GTX 590's standing among its nearest rivals, the data shows a tightly packed field. The AMD Radeon Pro 455 sits virtually at parity with a score of 12,831, a delta of 0%. The AMD FirePro W5100 trails by a razor-thin 0.1% at 12,847, and the AMD Radeon 740M is 0.3% behind at 12,870. The only rival the GTX 590 beats by a measurable amount in this grouping is the NVIDIA GeForce GTX 670, which scores 12,773, putting the GTX 590 0.4% ahead. This places the GTX 590 in the 52nd percentile of all GPUs in the database, indicating that while it is a capable card, it sits just above the midpoint of the performance distribution.

The MX350's rival grouping tells a different story. Its average benchmark score across OpenCL and Vulkan tests is 10,883, which puts it in the 49th percentile. The AMD Radeon Pro 450 scores 10,804, meaning the MX350 is 0.7% ahead. The NVIDIA Quadro K2200 trails by 1.1% with a score of 10,761. On the other side, the NVIDIA GeForce GTX 1650 SUPER leads the MX350 by 1.5% at 11,047, and the AMD Radeon RX 550 is 1.7% ahead at 11,075. The MX350's OpenCL score of 8,689 is its weaker result, while its Vulkan score of 13,077 is substantially higher, suggesting the card performs significantly better under the Vulkan API than under OpenCL.

When comparing the two cards directly, the GTX 590's OpenCL advantage of 47.7% is the headline number. However, it is importantly the MX350's Vulkan score of 13,077 exceeds the GTX 590's OpenCL score of 12,830. The database does not include a Vulkan result for the GTX 590, so a direct cross-API comparison is not possible, but the number indicates that the MX350 is not universally slower in every workload.

Where Each One Wins

The GTX 590 wins the only direct head-to-head benchmark, taking the OpenCL test with a 47.7% margin. This result aligns with its higher absolute compute throughput. The GTX 590 delivers 1,244.2 GFLOPS of FP32 performance, whereas the MX350 delivers 1.879 TFLOPS, which is equivalent to 1,879 GFLOPS. Despite the MX350's higher raw FP32 figure, the OpenCL benchmark result favors the GTX 590, indicating that real-world API performance depends on more than just theoretical throughput. The GTX 590 also has a much wider memory bus at 384 bits versus 64 bits, and significantly higher memory bandwidth at 164.0 GB/s versus 56.06 GB/s, which likely contributes to its OpenCL advantage.

The MX350 wins in scenarios that favor its architecture and feature set. It supports Vulkan 1.4, while the GTX 590 has no recorded Vulkan support in the database. Its DirectX 12 support is listed as 12_1, whereas the GTX 590 is listed as 12 (11_0), meaning the MX350 has a higher feature level. The MX350 also has a much higher transistor density at 25.0M per mm² versus 5.8M per mm², reflecting its modern 14 nm process node compared to the GTX 590's 40 nm node. For portable or low-power applications, the MX350 is the clear choice: its 20 W TDP is a fraction of the GTX 590's 365 W, and it requires no power connectors, whereas the GTX 590 needs two 8-pin connectors and a 750 W suggested power supply.

The GTX 590 wins on pixel rate and texture rate, posting 19.46 GPixel/s and 38.91 GTexel/s, respectively. The MX350 counters with 23.49 GPixel/s and 46.98 GTexel/s, meaning the MX350 is actually faster in both fill rates. However, the GTX 590 has more TMUs at 64 versus 32 and more ROPs at 48 versus 16, so the per-clock efficiency of the MX350 is higher. The GTX 590 also has more shading units at 512 versus 640, though the MX350 has more in absolute terms. The database records one win for the GTX 590 and zero for the MX350 in direct comparison, but that single test does not capture the full picture of where each card excels.

FAQ

Q: Which GPU has the higher benchmark score in the direct comparison?

A: The NVIDIA GeForce GTX 590 scores 12,830 in Geekbench OpenCL, while the NVIDIA GeForce MX350 scores 8,689. The GTX 590 leads by 47.7%.

Q: How does the MX350's Vulkan performance compare to the GTX 590's OpenCL performance?

A: The MX350 scores 13,077 in Geekbench Vulkan, which is higher than the GTX 590's OpenCL score of 12,830. The GTX 590 has no recorded Vulkan benchmark in the database.

Q: What is the memory bandwidth difference between the two cards?

A: The GTX 590 has a memory bandwidth of 164.0 GB/s, while the MX350 has 56.06 GB/s. The GTX 590 also uses a 384-bit bus width compared to the MX350's 64-bit bus.

Q: Which GPU has a higher FP32 compute throughput?

A: The MX350 delivers 1.879 TFLOPS, which is higher than the GTX 590's 1,244.2 GFLOPS. Despite this, the GTX 590 wins the OpenCL benchmark.

Q: What are the power requirements for each GPU?

A: The GTX 590 has a TDP of 365 W and requires two 8-pin power connectors with a suggested 750 W power supply. The MX350 has a TDP of 20 W and uses no power connectors, making it suitable for portable devices.

Q: Which GPU supports a higher DirectX feature level?

A: The MX350 supports DirectX 12_1, while the GTX 590 supports DirectX 12 (11_0). The MX350 also supports Vulkan 1.4, while the GTX 590 has no listed Vulkan support.

Specification Differences

The two GPUs differ substantially across nearly every specification category. The GTX 590 uses the GF110 chip on a 40 nm process node from TSMC, while the MX350 uses the GP107S chip on a 14 nm process node from Samsung. The GTX 590 has 3,000 million transistors on a 520 mm² die, giving a transistor density of 5.8M per mm². The MX350 has 3,300 million transistors on a 132 mm² die, resulting in a density of 25.0M per mm². The MX350's die is about a quarter of the size but packs more transistors.

Clock speeds differ significantly. The GTX 590 does not have recorded base or boost clocks, only a memory clock of 854 MHz, which translates to 3.4 Gbps effective. The MX350 has a base clock of 1354 MHz and a boost clock of 1468 MHz, with a memory clock of 1752 MHz or 7 Gbps effective.

Memory configurations are also different. The GTX 590 has 1536 MB of GDDR5 on a 384-bit bus, while the MX350 has 2 GB of GDDR5 on a 64-bit bus. The GTX 590's bandwidth is 164.0 GB/s versus the MX350's 56.06 GB/s.

Compute resources vary. The GTX 590 has 512 shading units, 64 TMUs, and 48 ROPs. The MX350 has 640 shading units, 32 TMUs, and 16 ROPs. The GTX 590 has higher pixel rate at 19.46 GPixel/s and texture rate at 38.91 GTexel/s, while the MX350 has higher rates at 23.49 GPixel/s and 46.98 GTexel/s. The FP32 figures are 1,244.2 GFLOPS for the GTX 590 and 1.879 TFLOPS for the MX350. The MX350 also has a recorded FP16 figure of 29.36 GFLOPS with a 1:64 ratio, while the GTX 590 has no recorded FP16 value.

Power and physical specifications differ dramatically. The GTX 590 has a TDP of 365 W, is dual-slot, uses two 8-pin power connectors, and has a suggested PSU of 750 W. It measures 279 mm in length, 111 mm in height, and 40 mm in width. The MX350 has a TDP of 20 W, no power connectors, no suggested PSU, and no recorded dimensions. The GTX 590 uses PCIe 2.0 x16, while the MX350 uses PCIe 3.0 x4. The GTX 590 has display outputs of 3x DVI and 1x mini-DisplayPort, while the MX350's outputs are listed as portable device dependent.

The GTX 590's DirectX support is 12 (11_0), OpenGL 4.6, and no Vulkan. The MX350 supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The GTX 590 was released on 2011-03-23, while the MX350 was released on 2020-02-09. The GTX 590 has a launch MSRP of 699 USD, while the MX350 has no recorded launch MSRP. The GTX 590's production status is end-of-life, as is the MX350's. The GTX 590 has a predecessor in GeForce 400 and a successor in GeForce 600, while the MX350 has no recorded predecessor or successor.

Architecture Differences

The architectural gap between these two GPUs is generational. The GTX 590 is built on Fermi 2.0 architecture, part of the GeForce 500 series, while the MX350 uses the Pascal architecture, part of the GeForce MX (3xx) series. Fermi 2.0 was designed for high-end desktop performance in 2011, while Pascal is a more efficient architecture from 2020 designed for mobility and mainstream use.

The process technology illustrates the leap. The GTX 590 uses a 40 nm node at TSMC, while the MX350 uses a 14 nm node at Samsung. This explains the density difference: the GTX 590 spreads 3,000 million transistors across 520 mm², while the MX350 fits 3,300 million transistors into just 132 mm². The smaller node allows for higher clock speeds and lower power consumption, which is reflected in the MX350's 20 W TDP versus the GTX 590's 365 W.

The memory architecture is a point of divergence. The GTX 590 uses a 384-bit memory bus, which was designed for maximum bandwidth in a dual-GPU flagship. The MX350 uses a 64-bit bus, reflecting its role as a power-efficient mobile GPU. Despite the smaller bus, the MX350's faster memory clock of 1752 MHz (7 Gbps effective) partially compensates, but the GTX 590's 164.0 GB/s bandwidth remains nearly three times higher.

Shading and texture resources differ in configuration. The MX350 has more shading units (640 versus 512) but fewer TMUs (32 versus 64) and fewer ROPs (16 versus 48). The GTX 590's higher ROP count gives it an advantage in certain rasterization workloads, even though the MX350 posts higher fill rates in the recorded data. The FP32 throughput numbers favor the MX350 at 1.879 TFLOPS, but the OpenCL benchmark shows the GTX 590 winning, indicating that architectural efficiency and memory bandwidth play a larger role in that specific workload.

API support is a clear differentiator. The GTX 590 is limited to DirectX 12 (11_0) and has no Vulkan support, while the MX350 supports DirectX 12 (12_1) and Vulkan 1.4. This means the MX350 is compatible with modern APIs and feature levels, while the GTX 590 is constrained to older API versions. Both support OpenGL 4.6.

The physical design reflects their intended use cases. The GTX 590 is a dual-slot card measuring 279 mm by 111 mm by 40 mm, requiring two 8-pin power connectors and a 750 W power supply. The MX350 has no recorded dimensions or power connectors, as it is designed for portable devices where space and power are limited. The bus interfaces differ as well: the GTX 590 uses PCIe 2.0 x16, while the MX350 uses PCIe 3.0 x4. The GTX 590's display outputs include 3x DVI and 1x mini-DisplayPort, while the MX350's outputs are dependent on the host device.

The release timeline shows the generational gap: the GTX 590 launched in March 2011, while the MX350 launched in February 2020, a span of nearly nine years. The GTX 590 is part of a lineage with a predecessor in GeForce 400 and a successor in GeForce 600, while the MX350 has no recorded lineage. These architectural differences explain why the GTX 590 can win an OpenCL benchmark despite being older: its high-bandwidth memory subsystem and high ROP count remain competitive, while the MX350's strengths lie in efficiency, modern API support, and portability.