AMD Radeon R9 M375 vs NVIDIA GeForce GTX 1660 Comparison

Head-to-Head Benchmarks

The recorded data contains two direct comparison points between the NVIDIA GeForce GTX 1660 and the AMD Radeon R9 M375, and both belong to the NVIDIA part. In Geekbench OpenCL, the GTX 1660 scores 47,850 against 10,457 for the R9 M375, a delta of 357.6% in favor of the newer card. The Vulkan test is even more lopsided: 50,137 versus 9,682, producing a 417.8% advantage for the GTX 1660. These are not marginal wins; the NVIDIA card delivers roughly four to five times the compute throughput in these workloads, depending on the API.

The overall average benchmark score reinforces the gap. The GTX 1660 sits at 11,680 across all recorded tests, while the R9 M375 averages 10,070. That difference, about 16%, is far smaller than the head-to-head deltas suggest, because the R9 M375 only has two benchmark entries in the database, both of which are compute-oriented. The GTX 1660 has ten entries spanning DirectX 9 through DirectX 12, OpenCL, Vulkan, and 2D tests, so its average reflects a broader workload mix.

Looking at the nearest rivals for each card puts the gap in context. The GTX 1660's closest competitor is the AMD Radeon RX 7800 XT, with an average score of 11,627, a delta of 0.5%. The NVIDIA card is also within 1.3% of the AMD Radeon Pro 5500M (11,528) and 1.8% of the NVIDIA Tesla K20c (11,479). The only rival it trails is the AMD Radeon RX 6500 XT at 11,842, a 1.4% deficit. These are tight margins, meaning the GTX 1660 slots into a performance band where small changes in driver or test conditions could reorder the rankings.

The R9 M375's nearest rivals are similarly close to each other. The NVIDIA Quadro K5100M averages 10,043, just 0.3% behind the AMD card. The AMD Radeon Pro 5300M is 0.6% behind at 10,013, and the NVIDIA GeForce GTX 870M trails by 1.1% at 9,959. The one rival ahead is the NVIDIA GeForce GTX 950A at 10,273, a 2% advantage for that part. So while the R9 M375 is below the GTX 1660 by a wide margin, it is competitive with a cluster of older mid-range mobile and workstation GPUs.

The head-to-head win count is 2 for the GTX 1660 and 0 for the R9 M375. No recorded test shows the AMD card ahead. The percentile data places the GTX 1660 at the 51st percentile among all GPUs, while the R9 M375 sits at the 48th percentile. That is a modest gap in global standing, but the percentile is computed across all GPUs, including many far weaker and far stronger parts, so the two cards land near the middle of the distribution.

Architecture Differences

The GTX 1660 is built on NVIDIA's Turing architecture, using the TU116 chip fabricated on a 12 nm process at TSMC. The die measures 284 mm² and packs 6,600 million transistors, yielding a density of 23.2 million transistors per mm². The R9 M375 uses AMD's GCN 1.0 architecture, with the Tropo chip on a 28 nm process, also from TSMC. That die is 123 mm² with 1,500 million transistors, giving a density of 12.2 million per mm². The process node difference is substantial: 12 nm versus 28 nm, which explains part of the transistor density gap.

The GTX 1660 has 1,408 shading units, 88 texture mapping units, and 48 render output units. The R9 M375 has 640 shading units, 40 TMUs, and 16 ROPs. In raw compute, the GTX 1660 delivers 5.027 TFLOPS of FP32 performance, while the R9 M375 produces 1,299.2 GFLOPS, roughly a factor of four. The GTX 1660 also supports FP16 at 10.05 TFLOPS with a 2:1 ratio, while the R9 M375 has no recorded FP16 capability.

Memory configurations differ sharply. The GTX 1660 uses 6 GB of GDDR5 on a 192-bit bus, with bandwidth of 192.1 GB/s. Memory clocks are 2001 MHz, or 8 Gbps effective. The R9 M375 uses 2 GB of DDR3 on a 128-bit bus, yielding only 28.80 GB/s of bandwidth. Its memory clock is 900 MHz, or 1800 Mbps effective. This is a 6.7x bandwidth advantage for the GTX 1660, which matters in texture-heavy and high-resolution workloads.

Pixel and texture rates also favor the GTX 1660. The NVIDIA card achieves 85.68 GPixel/s and 157.1 GTexel/s, while the R9 M375 manages 16.24 GPixel/s and 40.60 GTexel/s. The GTX 1660 has a base clock of 1530 MHz and a boost of 1785 MHz; the R9 M375 runs at 1000 MHz base and 1015 MHz boost. Both cards use PCIe 3.0 x16, so interface bandwidth is identical.

API support shows the GTX 1660 with DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The R9 M375 lists DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. The NVIDIA card has a newer Vulkan revision and a higher DirectX feature level. Neither card has ray tracing or tensor cores, so those fields are null for both.

Where Each One Wins

The GTX 1660 wins every recorded benchmark that overlaps between the two cards. In compute-focused tests like Geekbench OpenCL and Vulkan, the advantage is overwhelming, exceeding 350% in both cases. The card also has a much broader benchmark footprint, with entries for DirectX 10, DirectX 11, DirectX 12, DirectX 9, G2D, G3D, and GPU compute. Its PassMark G3D score of 11,646 and GPU compute score of 4,963 indicate strong rasterization and general compute performance relative to its own average.

The R9 M375 has no wins in the head-to-head data. Its only recorded benchmarks are Geekbench OpenCL at 10,457 and Geekbench Vulkan at 9,682. In those tests, it lands at roughly 22% of the GTX 1660's OpenCL score and 19% of its Vulkan score. The R9 M375's nearest rivals are all within 2% of its average, meaning it competes with the NVIDIA Quadro K5100M, AMD Radeon Pro 5300M, NVIDIA GeForce GTX 870M, and NVIDIA GeForce GTX 950A. It does not compete with the GTX 1660's performance tier.

For gaming and real-time graphics, the GTX 1660's advantages in pixel rate, texture rate, and memory bandwidth are decisive. The R9 M375's DDR3 memory and 128-bit bus create a bottleneck that the GTX 1660 does not face. For compute workloads such as OpenCL, the shading unit count and FP32 throughput make the GTX 1660 the clear choice. The R9 M375 is suitable only for older or lighter tasks, given its GCN 1.0 architecture and 28 nm process.

The GTX 1660 also has a higher percentile ranking at 51 versus 48, meaning it sits marginally higher in the global GPU distribution. That is a small difference, but it aligns with the average score gap. The R9 M375's nearest rivals cluster so tightly that its positioning is more sensitive to individual test results; a single outlier could shift its rank, whereas the GTX 1660 has a wider cushion above and below its nearest competitors.

The Verdict

The data points to a clear winner for any workload involving compute or modern graphics APIs. The NVIDIA GeForce GTX 1660 leads the AMD Radeon R9 M375 by 357.6% in OpenCL and 417.8% in Vulkan. Its average benchmark score is 16% higher, and it wins both head-to-head tests. The GTX 1660 also offers 6 GB of GDDR5 memory versus 2 GB of DDR3, a 192-bit bus versus 128-bit, and roughly four times the FP32 throughput.

The R9 M375 is not without merit in its own tier. It sits within 2% of four rival GPUs, so it is a competitive option among older mid-range parts. Its 1,299.2 GFLOPS of FP32 performance and 40.60 GTexel/s texture rate are adequate for basic 3D tasks, but they are not in the GTX 1660's league. The 28 nm process and GCN 1.0 architecture place it several generations behind the Turing-based GTX 1660.

For users choosing between these two, the GTX 1660 is the only sensible pick from the recorded metrics. It has higher scores in every overlapping test, a better memory subsystem, more shading units, and a newer architecture. The R9 M375 would only make sense if the workload is extremely light and the platform is constrained to its feature set, but the benchmark data does not support that choice for any measured task.

The GTX 1660's nearest rivals, all within 1.8% of its average score, indicate it sits at the boundary between mid-range and upper-mid-range performance. The R9 M375's rivals, all within 2%, show it is firmly in the lower-mid-range. The verdict from the database is unambiguous: the GTX 1660 is the superior card by every recorded metric.

FAQ

Q: How much faster is the NVIDIA GeForce GTX 1660 in Geekbench OpenCL?

A: The GTX 1660 scores 47,850 versus 10,457 for the R9 M375, a delta of 357.6% in favor of NVIDIA.

Q: What is the difference in Vulkan performance?

A: The GTX 1660 scores 50,137, while the R9 M375 scores 9,682, giving the NVIDIA card a 417.8% advantage.

Q: Which card has more memory bandwidth?

A: The GTX 1660 has 192.1 GB/s of bandwidth from 6 GB of GDDR5 on a 192-bit bus. The R9 M375 has 28.80 GB/s from 2 GB of DDR3 on a 128-bit bus.

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

A: The GTX 1660 averages 11,680 across all recorded tests, while the R9 M375 averages 10,070.

Q: How do the nearest rivals compare?

A: The GTX 1660's closest rival is the AMD Radeon RX 7800 XT at 0.5% delta, while the R9 M375's closest rival is the NVIDIA Quadro K5100M at 0.3% delta.

Q: Which card has a higher global percentile?

A: The GTX 1660 is at the 51st percentile among all GPUs, while the R9 M375 is at the 48th percentile.

Specification Differences

The two cards differ in nearly every specification field. The GTX 1660 uses a 12 nm process, while the R9 M375 uses 28 nm. Transistor count is 6,600 million versus 1,500 million, and die size is 284 mm² versus 123 mm². Transistor density is 23.2M per mm² for NVIDIA and 12.2M per mm² for AMD.

Clock speeds: the GTX 1660 runs at 1530 MHz base and 1785 MHz boost; the R9 M375 runs at 1000 MHz base and 1015 MHz boost. Memory clocks are 2001 MHz (8 Gbps effective) for NVIDIA and 900 MHz (1800 Mbps effective) for AMD.

Memory: the GTX 1660 has 6 GB GDDR5 on a 192-bit bus with 192.1 GB/s bandwidth. The R9 M375 has 2 GB DDR3 on a 128-bit bus with 28.80 GB/s bandwidth.

Shading units: 1,408 versus 640. TMUs: 88 versus 40. ROPs: 48 versus 16.

Pixel rate: 85.68 GPixel/s for NVIDIA, 16.24 GPixel/s for AMD. Texture rate: 157.1 GTexel/s versus 40.60 GTexel/s.

FP32: 5.027 TFLOPS versus 1,299.2 GFLOPS. FP16: 10.05 TFLOPS (2:1) for NVIDIA, null for AMD.

TDP: 120 W for the GTX 1660, null for the R9 M375. Slot width: dual-slot for NVIDIA, null for AMD. Power connectors: 1x 8-pin for NVIDIA, null for AMD. Suggested PSU: 300 W for NVIDIA, null for AMD.

Bus interface is PCIe 3.0 x16 for both. Display outputs: the GTX 1660 has 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a; the R9 M375 has null.

APIs: DirectX 12 (12_1) for NVIDIA, DirectX 12 (11_1) for AMD. OpenGL 4.6 for both. Vulkan 1.4 for NVIDIA, 1.2.170 for AMD.

Dimensions: the GTX 1660 is 229 mm (9 inches) long, 111 mm (4.4 inches) high, and 35 mm (1.4 inches) wide. The R9 M375 has null dimensions.

Release dates: March 13, 2019 for the GTX 1660, May 4, 2015 for the R9 M375. Production status is end-of-life for both. The GTX 1660 has a launch MSRP of 219 USD; the R9 M375 has no recorded MSRP.