AMD Radeon R7 M350 vs NVIDIA GeForce GTX 460 SE Comparison

The GeForce GTX 460 SE and the Radeon R7 M350 represent two very different eras of mobile and desktop GPU design, yet their aggregate benchmark scores land them within a single percentage point of each other. The NVIDIA card, a 2010 desktop part, and the AMD card, a 2015 mobile-oriented chip, are separated by roughly five years of architectural evolution, but the data shows they perform at a comparable level in compute workloads. The R7 M350 holds a narrow edge in the only direct head-to-head OpenCL test, while the GTX 460 SE counters with a slightly better overall percentile ranking among all GPUs.

Where Each One Wins

The Radeon R7 M350 is the clear winner in raw compute throughput as measured by the Geekbench OpenCL test. It scores 6991 points compared to the GTX 460 SE’s 6389, a difference of 8.6 percent. This is the only benchmark where the two are directly compared, and the AMD part takes it decisively. For applications that rely heavily on general-purpose GPU compute, such as OpenCL-accelerated rendering or scientific calculations, the R7 M350 is the stronger choice.

The GeForce GTX 460 SE, despite losing the head-to-head, holds a marginal edge in the broader ranking. Its percentile score of 37 versus the R7 M350’s 36 indicates that it sits slightly higher relative to the entire GPU landscape. This is a small but notable distinction; the older NVIDIA chip is just a bit more competitive against the full field of GPUs in the database, even though it trails the AMD part in their direct comparison. In practical terms, the two are nearly inseparable in overall standing, but the GTX 460 SE’s higher percentile suggests it may have slightly better performance consistency across a wider range of workloads.

The GTX 460 SE also wins on memory bandwidth by a massive margin. Its 256-bit bus and GDDR5 memory deliver 108.8 GB/s, while the R7 M350’s 64-bit bus and DDR3 memory manage only 16 GB/s. This 92.8 GB/s difference is the single largest specification gap between the two cards. For texture-heavy or bandwidth-sensitive tasks, the NVIDIA card is far better equipped, even if the AMD card’s higher raw compute score suggests it excels in other areas.

Architecture Differences

The two GPUs are built on fundamentally different architectures. The GTX 460 SE uses NVIDIA’s Fermi architecture, manufactured on a 40 nm process at TSMC. The chip, designated GF104, packs 1,950 million transistors into a 332 mm² die, giving it a transistor density of 5.9 million per square millimeter. The R7 M350, in contrast, uses AMD’s GCN 3.0 architecture on a 28 nm process, also at TSMC. Its Meso chip contains 1,550 million transistors on a much smaller 125 mm² die, achieving a density of 12.4 million per square millimeter — more than double the NVIDIA part’s density.

The compute layouts differ significantly. The GTX 460 SE has 288 shading units, 48 texture mapping units, and 32 ROPs. The R7 M350 has 384 shading units — 96 more — but only 24 TMUs and 8 ROPs, exactly half the TMUs and a quarter of the ROPs of the NVIDIA card. This explains why the AMD card scores higher in raw FP32 compute (779.5 GFLOPS vs 748.8 GFLOPS) but falls far behind in texture and pixel rates. The GTX 460 SE’s texture rate is 31.20 GTexel/s versus the R7 M350’s 24.36 GTexel/s, and its pixel rate is 7.800 GPixel/s versus 8.120 GPixel/s — a rare win for the AMD part in pixel throughput, likely due to its higher clock speeds.

The R7 M350 also supports FP16 compute at a 1:1 ratio with FP32, offering 779.5 GFLOPS of half-precision performance. The GTX 460 SE has no listed FP16 capability. The AMD card’s base clock is 1000 MHz with a boost of 1015 MHz, while the NVIDIA card has no base or boost clocks listed, only a memory clock of 850 MHz (3.4 Gbps effective). The R7 M350’s memory runs at 1000 MHz (2 Gbps effective). The AMD card also supports Vulkan 1.2.170 and DirectX 12 (12_0), while the NVIDIA card only lists DirectX 12 (11_0) with no Vulkan support.

Head-to-Head Benchmarks

The sole direct benchmark comparison is Geekbench OpenCL, where the Radeon R7 M350 wins with a score of 6991 against the GTX 460 SE’s 6389. That is an 8.6 percent advantage for the AMD card. This is a meaningful margin in compute performance. The R7 M350’s higher shading unit count — 384 versus 288 — and its newer GCN architecture likely drive this result, despite its much slower memory subsystem. The AMD card’s FP32 throughput of 779.5 GFLOPS exceeds the NVIDIA card’s 748.8 GFLOPS by about 30.7 GFLOPS, or roughly 4 percent, which partially explains the benchmark gap.

However, the GTX 460 SE is not without its own wins in the broader data. Its memory bandwidth of 108.8 GB/s is nearly seven times higher than the R7 M350’s 16 GB/s. This is a decisive advantage in any workload that requires moving large amounts of data, even if the OpenCL test does not reflect it. The NVIDIA card also has a higher texture fill rate (31.20 GTexel/s vs 24.36 GTexel/s), a 28 percent advantage, which matters for games and other texture-heavy applications. The GTX 460 SE’s pixel rate is slightly lower at 7.800 GPixel/s versus 8.120 GPixel/s, a 4 percent deficit that is unlikely to matter in most scenarios.

Looking at the nearest rivals for each card provides additional context. The GTX 460 SE’s closest competitor is the GeForce GTX 580M, which scores identically at 6389. The RTX PRO 5000 72 GB Blackwell sits just 0.3 percent higher at 6407, while the Radeon Pro WX 4100 is 0.9 percent lower at 6330. The R7 M350’s nearest rival is the Radeon Pro WX 4100 at 6330, with the Quadro K620 at 6282 (0.7 percent lower). Notably, the R7 M350’s rivals include the RTX 5070 Ti SUPER and RTX 4070 Ti SUPER AD102, both scoring 6270 — 0.9 percent lower. This shows that the R7 M350, despite its low bandwidth, holds its own against a wide range of modern and older GPUs.

FAQ

Q: Which GPU has a higher OpenCL benchmark score?

A: The AMD Radeon R7 M350 scores 6991 in Geekbench OpenCL, while the NVIDIA GeForce GTX 460 SE scores 6389. The AMD card is 8.6 percent faster in this test.

Q: How do their overall percentile rankings compare?

A: The GTX 460 SE ranks in the 37th percentile of all GPUs, while the R7 M350 ranks in the 36th percentile. The NVIDIA card is one percentile point higher despite losing the direct benchmark.

Q: What is the biggest specification gap between the two cards?

A: Memory bandwidth. The GTX 460 SE delivers 108.8 GB/s over a 256-bit GDDR5 bus, while the R7 M350 offers only 16 GB/s over a 64-bit DDR3 bus. This is a 92.8 GB/s difference.

Q: Which card has more shading units?

A: The R7 M350 has 384 shading units, compared to 288 on the GTX 460 SE. The AMD card also has a higher FP32 compute rate at 779.5 GFLOPS versus 748.8 GFLOPS.

Q: Does either card support Vulkan?

A: Only the Radeon R7 M350 lists Vulkan support, at version 1.2.170. The GTX 460 SE has no Vulkan support listed and only supports DirectX 12 (11_0), while the AMD card supports DirectX 12 (12_0).

Q: What are their process nodes and die sizes?

A: The GTX 460 SE is built on a 40 nm process with a 332 mm² die. The R7 M350 uses a 28 nm process with a 125 mm² die, making it much smaller and denser.

Specification Differences

The two cards differ on nearly every key specification. The GTX 460 SE is built on a 40 nm process, while the R7 M350 uses 28 nm. Transistor counts are 1,950 million versus 1,550 million, and die sizes are 332 mm² versus 125 mm². Transistor density is 5.9M per mm² on the NVIDIA card and 12.4M per mm² on the AMD card.

The R7 M350 has a base clock of 1000 MHz and a boost clock of 1015 MHz; the GTX 460 SE has no base or boost clocks listed. Memory clocks are 850 MHz (3.4 Gbps effective) on the NVIDIA card and 1000 MHz (2 Gbps effective) on the AMD card. Memory size is 1024 MB of GDDR5 on the GTX 460 SE versus 4 GB of DDR3 on the R7 M350. Bus widths are 256 bit versus 64 bit, and bandwidth is 108.8 GB/s versus 16 GB/s.

Shading units are 288 versus 384, TMUs are 48 versus 24, and ROPs are 32 versus 8. Pixel rates are 7.800 GPixel/s versus 8.120 GPixel/s. Texture rates are 31.20 GTexel/s versus 24.36 GTexel/s. FP32 compute is 748.8 GFLOPS versus 779.5 GFLOPS, with the AMD card adding 779.5 GFLOPS of FP16 performance. The GTX 460 SE has a TDP of 150 W, is dual-slot, requires 2x 6-pin power connectors and a 450 W PSU, and uses PCIe 2.0 x16. The R7 M350 has no TDP, slot width, power connector, or PSU data, and uses PCIe 3.0 x8. Display outputs are 2x DVI and 1x mini-HDMI 1.3a on the NVIDIA card, with none listed for the AMD card. The GTX 460 SE measures 210 mm (8.3 inches) in length; the R7 M350 has no dimensions listed. Launch MSRP for the GTX 460 SE was 160 USD; the R7 M350 has no MSRP data.