NVIDIA GeForce GTX 1660 SUPER vs NVIDIA GeForce MX350 Comparison

Head-to-Head Benchmarks

The recorded data shows a decisive victory for the NVIDIA GeForce GTX 1660 SUPER across the two shared benchmark workloads. In Geekbench OpenCL, the GTX 1660 SUPER scores 52,490 against the MX350's 8,689, a delta of 504.1%. This is not a marginal gap; the desktop card outperforms the mobile part by a factor of roughly six in raw compute throughput as measured by this test. The Vulkan result tells a similar story: 57,102 for the GTX 1660 SUPER versus 13,077 for the MX350, a 336.7% advantage. Both wins belong to the GTX 1660 SUPER, giving it a 2-0 sweep in the head-to-head comparison.

The magnitude of these deltas is worth pausing on. A 504.1% lead in OpenCL suggests that the GTX 1660 SUPER is operating in a completely different performance class, not merely a slightly faster tier. The Vulkan delta, while still enormous at 336.7%, is somewhat smaller, which may hint at different scaling behavior between the two APIs for these architectures. The MX350's nearest rivals in the database, such as the AMD Radeon Pro 450 (average score 10,804) and the NVIDIA Quadro K2200 (10,761), sit far below the GTX 1660 SUPER's average of 12,986. Meanwhile, the GTX 1660 SUPER's closest competitors include the NVIDIA GeForce RTX 3050 Ti Mobile (12,940) and the AMD Radeon RX 580 (12,928), both within 0.4% of its average score. The MX350's own nearest rivals, including the NVIDIA GeForce GTX 1650 SUPER (11,047) and AMD Radeon RX 550 (11,075), still trail the GTX 1660 SUPER's average by a wide margin.

Architecture Differences

The two GPUs come from different architectural generations, and the data reflects that divide clearly. The GTX 1660 SUPER is built on the Turing architecture, using the TU116 chip fabricated at TSMC on a 12 nm process. It packs 6,600 million transistors across a 284 mm² die, yielding a transistor density of 23.2 million per square millimeter. The MX350, by contrast, uses the older Pascal architecture with the GP107S chip, manufactured by Samsung on a 14 nm process. It contains 3,300 million transistors on a 132 mm² die, with a slightly higher transistor density of 25.0 million per square millimeter. The denser packing on the smaller chip is notable, but it does not translate into competitive performance.

Clock behavior also differs substantially. The GTX 1660 SUPER runs at a base clock of 1530 MHz and boosts to 1785 MHz, while the MX350 operates at a lower 1354 MHz base and 1468 MHz boost. Memory configurations diverge even more sharply. The GTX 1660 SUPER uses 6 GB of GDDR6 across a 192-bit bus, delivering 336.0 GB/s of bandwidth at 14 Gbps effective. The MX350 has 2 GB of GDDR5 on a 64-bit bus, with 56.06 GB/s of bandwidth at 7 Gbps effective. That is a six-fold difference in memory bandwidth, which echoes the six-fold difference in OpenCL performance.

The compute resources tell a similar story. The GTX 1660 SUPER has 1408 shading units, 88 texture mapping units, and 48 raster output units. The MX350 has 640 shading units, 32 TMUs, and 16 ROPs. Pixel rate for the GTX 1660 SUPER is 85.68 GPixel/s versus 23.49 GPixel/s for the MX350. Texture rate is 157.1 GTexel/s versus 46.98 GTexel/s. FP32 throughput stands at 5.027 TFLOPS for the GTX 1660 SUPER and 1.879 TFLOPS for the MX350. FP16 performance is particularly lopsided: the GTX 1660 SUPER achieves 10.05 TFLOPS with a 2:1 ratio, while the MX350 manages only 29.36 GFLOPS at a 1:64 ratio, meaning it has negligible FP16 capability by comparison.

Both cards support DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. Neither has ray tracing cores or tensor cores. The power envelopes differ drastically: the GTX 1660 SUPER is rated at 125 W TDP and requires a single 8-pin power connector with a suggested 300 W power supply, while the MX350 is a 20 W part with no power connectors, typical of a mobile implementation. The MX350 also uses a narrower PCIe 3.0 x4 interface versus the GTX 1660 SUPER's PCIe 3.0 x16.

Where Each One Wins

The GTX 1660 SUPER wins every shared benchmark, so the use-case split is heavily weighted toward the desktop card. For users running OpenCL workloads, the 504.1% advantage means tasks like GPU-accelerated compute, rendering, or data processing will complete in a fraction of the time. The Vulkan advantage of 336.7% points to strong performance in modern graphics APIs, which matters for gaming and real-time visualization. The GTX 1660 SUPER's average benchmark score of 12,986 places it in the 53rd percentile of all GPUs in the database, while the MX350 sits at the 49th percentile with an average of 10,883. The percentile gap is modest, but the average score gap of 19.5% is substantial.

The MX350's wins are narrower in context. Its nearest rivals include the NVIDIA GeForce GTX 1650 SUPER at 11,047, which is only 1.5% ahead of the MX350, and the AMD Radeon RX 550 at 11,075 at 1.7% ahead. These are close margins, suggesting the MX350 is competitive with entry-level desktop cards from the previous generation. The MX350's strength lies in scenarios where power consumption matters, but the database does not record any benchmark where it wins outright against the GTX 1660 SUPER. For a mobile GPU bound by thermal and power limits, the 20 W MX350 is the only option that fits, but users should expect roughly a fifth to a sixth of the GTX 1660 SUPER's performance in compute tasks.

FAQ

Q: Which GPU wins in Geekbench OpenCL, and by how much?

A: The NVIDIA GeForce GTX 1660 SUPER wins with a score of 52,490 against the MX350's 8,689, a 504.1% delta, making the advantage roughly six times the MX350's result in absolute terms.

Q: Is the GTX 1660 SUPER's FP32 performance compared to the MX350?

A: The GTX 1660 SUPER achieves 5.027 TFLOPS in FP32, while the MX350 delivers 1.850 TFLOPS, a gap that complements the OpenCL delta and highlights a roughly 2.7x difference in raw shader throughput.

Q: How much memory bandwidth do the two cards have, and does it affect performance?

A: The GTX 1660 SUPER has 336.0 GB/s of memory bandwidth against the MX350's 56.06 GB/s, a six-fold difference that likely contributes to the 504.1% OpenCL and 336.7% Vulkan deltas in the head-to-head results.

Q: Which card has a higher boost clock?

A: The GTX 1660 SUPER boosts to 1785 MHz, while the MX350 boosts to 1468 MHz, a difference of 317 MHz in favor of the desktop card.

Q: What are the average benchmark scores for each GPU?

A: The GTX 1660 SUPER records an average score of 12,986, while the MX350 averages 10,883, a difference that places the GTX 1660 SUPER at the 53rd percentile versus the MX350's 49th percentile.

Q: Does the MX350 have any advantage in power consumption?

A: The MX350 is rated at 20 W TDP with no power connectors, while the GTX 1660 SUPER is rated at 125 W with a single 8-pin connector and a suggested 300 W power supply, though this is a specification difference rather than a performance result.

The Verdict

The data points to a straightforward conclusion: the NVIDIA GeForce GTX 1660 SUPER is the superior performer in every benchmark the two share. Its 504.1% lead in OpenCL and 336.7% lead in Vulkan are not close calls; they reflect a fundamental difference in compute capability, memory bandwidth, and shader throughput. The GTX 1660 SUPER's 5.027 TFLOPS FP32 and 336.0 GB/s bandwidth dwarf the MX350's 1.879 TFLOPS and 56.06 GB/s, and its 6 GB GDDR6 frame buffer offers more headroom for modern workloads than the 2 GB GDDR5 on the MX350. The MX350, however, is a 20 W mobile part, and its low power draw makes it suitable for thin laptops where the GTX 1660 SUPER's 125 W TDP and dual-slot footprint are impossible. For users who need a discrete GPU in a portable chassis, the MX350 is the only viable option between the two, but the recorded data shows it will deliver roughly a fifth of the GTX 1660 SUPER's compute performance in OpenCL and about a quarter in Vulkan. For anyone with the space and power budget for a desktop card, the GTX 1660 SUPER is the clear choice, and its average score of 12,986 places it within 0.4% of the RTX 3050 Ti Mobile and within 0.7% of the Tesla M2090, making it competitive with more recent mobile parts despite its end-of-life status.

Specification Differences

The GTX 1660 SUPER uses the TU116 chip on a 12 nm TSMC process, while the MX350 uses the GP107S on a 14 nm Samsung process. Transistor counts are 6,600 million versus 3,300 million, and die sizes are 284 mm² versus 132 mm². The GTX 1660 SUPER has a base clock of 1530 MHz and boost of 1785 MHz; the MX350 has a base of 1354 MHz and boost of 1468 MHz. Memory differs in size (6 GB GDDR6 versus 2 GB GDDR5), bus width (192-bit versus 64-bit), bandwidth (336.0 GB/s versus 56.06 GB/s), and effective speed (14 Gbps versus 7 Gbps). Shading units are 1408 versus 640, TMUs are 88 versus 32, and ROPs are 48 versus 16. Pixel rate is 85.68 GPixel/s versus 23.49 GPixel/s, texture rate is 157.1 GTexel/s versus 46.98 GTexel/s, and FP32 is 5.027 TFLOPS versus 1.879 TFLOPS. FP16 is 10.05 TFLOPS versus 29.36 GFLOPS. TDP is 125 W versus 20 W. The GTX 1660 SUPER has a dual-slot design, 1x 8-pin power connector, a suggested 300 W power supply, and PCIe 3.0 x16 interface. The MX350 has no power connectors and uses PCIe 3.0 x4. Display outputs are 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a for the GTX 1660 SUPER, while the MX350 is described as portable device dependent. The GTX 1660 SUPER measures 229 mm in length, 111 mm in height, and 35 mm in width; the MX350 has no recorded dimensions. The GTX 1660 SUPER launched with an MSRP of 229 USD, while the MX350 has no recorded launch MSRP.