AMD Radeon R9 M275X vs NVIDIA GeForce GTX 1660 Comparison

# Head-to-Head Benchmarks

The benchmark data shows a decisive, one-sided contest between the NVIDIA GeForce GTX 1660 and the AMD Radeon R9 M275X. In the two shared tests — Geekbench OpenCL and Geekbench Vulkan — the NVIDIA card wins both, with margins that are nothing short of overwhelming. The GeForce GTX 1660 scores 47,850 in Geekbench OpenCL, a staggering 327.2% ahead of the R9 M275X's 11,200. In Geekbench Vulkan, the gap widens further: the GTX 1660 posts 50,137 against just 9,964 for the AMD part, a 403.2% advantage.

These are not subtle differences. The GTX 1660 is not merely faster; it is in a different performance class entirely. In OpenCL compute workloads, the NVIDIA card delivers more than four times the raw score of its AMD rival. The Vulkan result is even more lopsided, with the GTX 1660 exceeding the R9 M275X by a factor of five. For any application leveraging these APIs — whether gaming, content creation, or general GPU compute — the GTX 1660 holds an insurmountable lead.

Context from the wider benchmark pool reinforces this dominance. The GTX 1660's average benchmark score across all tests is 11,680, placing it in the 51st percentile of all GPUs. Its nearest rivals include the AMD Radeon RX 7800 XT (avg score 11,627, delta +0.5%), the AMD Radeon Pro 5500M (11,528, +1.3%), and the AMD Radeon RX 6500 XT (11,842, -1.4%). The GTX 1660 sits comfortably in this mid-range cluster, trading blows with cards that are far more modern. The R9 M275X, by contrast, averages 10,582 across its benchmark results, landing in the 49th percentile. Its nearest rivals — the AMD Radeon RX 6600S (10,629, -0.4%), AMD Radeon RX 550X (10,481, +1%), and NVIDIA GeForce GTX 560 Ti (10,690, -1%) — are all older or lower-tier parts. The gap between the two cards' average scores is roughly 1,100 points, or about 10.4%.

Looking at the individual benchmark suite, the GTX 1660 shows broad strength. In Passmark G3D, it scores 11,646, while in Passmark GPU Compute it manages 4,963. Its DirectX 9 score of 177 and DirectX 11 score of 79 indicate solid legacy API performance, while DirectX 10 (61) and DirectX 12 (49) are comparatively lower but still respectable. The GeForce card also posts a Passmark G2D score of 776, reflecting capable 2D and desktop compositing performance. The R9 M275X, lacking these additional benchmark results, cannot be compared on those fronts — only the two Geekbench tests overlap.

# The Verdict

The data is unambiguous: the NVIDIA GeForce GTX 1660 is the superior product by every measurable metric. If you are choosing between these two for any workload — gaming, compute, or general use — the GTX 1660 is the only rational pick. It wins both head-to-head benchmarks by margins of 327.2% and 403.2%, and its average benchmark score of 11,680 dwarfs the R9 M275X's 10,582.

The R9 M275X is a legacy part, released in 2014, and its performance reflects its age. Its 49th percentile ranking places it below the GTX 1660's 51st percentile, and its nearest rivals are all similarly dated or low-end components. There is no scenario in which the AMD card's data suggests it can compete with the GTX 1660. The GTX 1660 also benefits from a more modern feature set, which we will examine in the architecture section, but even on raw numbers alone, the verdict is clear.

One potential caveat: the GTX 1660 has a launch MSRP of 219 USD, which is a factual data point but not a recommendation either way. For users with legacy system constraints — such as a motherboard that cannot support a dual-slot, 8-pin powered card — the R9 M275X might be the only physical option, though its performance ceiling is dramatically lower. Otherwise, the GTX 1660 is the definitive choice from the available data.

# Architecture Differences

The two GPUs come from different eras and entirely different architectural lineages. The NVIDIA GeForce GTX 1660 is built on the Turing architecture, manufactured by TSMC on a 12 nm process. It uses the TU116 chip, which packs 6,600 million transistors into a 284 mm² die, yielding a transistor density of 23.2 million per square millimeter. The Turing architecture brings modern features such as support for DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4, along with a 2:1 FP16 ratio that enables 10.05 TFLOPS of half-precision compute.

The AMD Radeon R9 M275X, in contrast, is based on the GCN 1.0 architecture, also fabricated by TSMC but on an older 28 nm process. Its Venus chip contains just 1,500 million transistors on a 123 mm² die, with a transistor density of 12.2 million per square millimeter — roughly half the density of the NVIDIA part. GCN 1.0 is a first-generation design that lacks the efficiency and feature set of Turing. The R9 M275X supports DirectX 12 (11_1) — a lower feature level than the GTX 1660's 12_1 — along with OpenGL 4.6 and Vulkan 1.2.170. Notably, the AMD card has no FP16 capability listed, whereas the GTX 1660 offers 10.05 TFLOPS of FP16 compute.

The architectural gap also shows in memory and compute resources. The GTX 1660 features 1,408 shading units, 88 texture mapping units, and 48 ROPs, with a pixel rate of 85.68 GPixel/s and a texture rate of 157.1 GTexel/s. Its FP32 throughput is 5.027 TFLOPS. The R9 M275X has just 640 shading units, 40 TMUs, and 16 ROPs, resulting in a pixel rate of 14.80 GPixel/s and a texture rate of 37.00 GTexel/s. Its FP32 performance is 1,184 GFLOPS — less than a quarter of the GTX 1660's. Neither card has ray tracing or tensor cores, so those AI and RT workloads are absent from both.

# Specification Differences

The specification tables reveal stark contrasts across nearly every field. The GTX 1660 runs at a base clock of 1530 MHz with a boost of 1785 MHz, while the R9 M275X operates at just 900 MHz base and 925 MHz boost. Memory configurations diverge sharply: the NVIDIA card has 6 GB of GDDR5 on a 192-bit bus, delivering 192.1 GB/s of bandwidth at 2001 MHz (8 Gbps effective). The AMD card offers only 2 GB of GDDR5 on a 128-bit bus, with bandwidth capped at 72.00 GB/s and a memory clock of 1125 MHz (4.5 Gbps effective). That is a 2.7x difference in memory bandwidth alone.

The GTX 1660 is a dual-slot card measuring 229 mm in length, 111 mm in height, and 35 mm in width. It requires a single 8-pin power connector and a 300 W suggested PSU, with a TDP of 120 W. The R9 M275X has no listed dimensions, power connectors, suggested PSU, or TDP in the data, making direct power comparisons impossible. The NVIDIA card provides display outputs of 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a; the AMD card's display outputs are not specified.

Release dates underscore the generational chasm: the GTX 1660 launched on 2019-03-13, while the R9 M275X arrived on 2014-01-27 — over five years earlier. Both are end-of-life products, but the GTX 1660 belongs to the GeForce 16 generation, with a predecessor in GeForce 10 and a successor in GeForce 20. The AMD card is part of the Gem System (R9 M200) generation, succeeding Solar System and preceding Polaris Mobile. The GTX 1660 has a launch MSRP of 219 USD; the R9 M275X has no launch MSRP listed.

# FAQ

Q: Which GPU is faster in Geekbench OpenCL?

A: The NVIDIA GeForce GTX 1660 scores 47,850 compared to the AMD Radeon R9 M275X's 11,200, a 327.2% advantage for the NVIDIA card.

Q: How do the two cards compare in Vulkan performance?

A: The GTX 1660 posts 50,137 in Geekbench Vulkan versus 9,964 for the R9 M275X, making the NVIDIA card 403.2% faster.

Q: What are the memory specifications of each card?

A: The GTX 1660 has 6 GB of GDDR5 on a 192-bit bus with 192.1 GB/s bandwidth. The R9 M275X has 2 GB of GDDR5 on a 128-bit bus with 72.00 GB/s bandwidth.

Q: What is the transistor count and die size difference?

A: The GTX 1660 contains 6,600 million transistors on a 284 mm² die, while the R9 M275X has 1,500 million transistors on a 123 mm² die.

Q: Which card has a higher pixel fill rate?

A: The GTX 1660 achieves 85.68 GPixel/s, whereas the R9 M275X manages only 14.80 GPixel/s.

Q: What are the release dates for these GPUs?

A: The GTX 1660 was released on 2019-03-13, while the R9 M275X was released on 2014-01-27.