AMD Radeon R5 M320 vs NVIDIA GeForce GTX 460M Comparison

The AMD Radeon R5 M320 and NVIDIA GeForce GTX 460M are both end-of-life mobile graphics processors, but they represent fundamentally different eras of GPU design. The data shows a clear overall winner in the AMD Radeon R5 M320, which achieves an average benchmark score of 4657 compared to the GTX 460M’s 4282, a difference of 8.8%. However, the story is more nuanced than a simple performance gap, as the two chips employ vastly different architectures, memory configurations, and feature sets that dictate their respective strengths and weaknesses.

The Verdict

Based strictly on the benchmark data, the AMD Radeon R5 M320 is the superior choice for general compute and graphics workloads. Its Geekbench OpenCL score of 5051 is 18% higher than the GTX 460M’s 4282 in the same test, and its average benchmark score of 4657 places it in the 27th percentile of all GPUs, two points higher than the GTX 460M’s 25th percentile. The R5 M320 also benefits from a larger 4 GB memory allocation versus the GTX 460M’s 1536 MB, which can be a practical advantage in memory-intensive applications.

However, the GTX 460M is not without its merits. Despite its lower raw compute scores, it offers a significantly wider 192-bit memory bus and higher memory bandwidth of 60.00 GB/s, compared to the R5 M320’s 64-bit bus and 16.00 GB/s. This makes the GTX 460M potentially better suited for tasks that are highly sensitive to memory throughput rather than raw shader count. The GTX 460M also has more texture mapping units (32 vs 20) and render output units (24 vs 8), which could translate to better fill-rate performance in specific rendering scenarios.

For a user prioritizing raw compute performance, modern API support, and larger memory capacity, the R5 M320 is the clear pick. For those working with older software that favors memory bandwidth and texture throughput, the GTX 460M may still hold up. The data does not support the GTX 460M as an overall winner, but it does highlight specific areas where it can compete.

Architecture Differences

The architectural divide between these two GPUs is stark. The AMD Radeon R5 M320 is built on the Graphics Core Next (GCN) 1.0 architecture using the small "Jet" chip, manufactured on a 28 nm process at TSMC. This process allows for a transistor density of 12.3 million per square millimeter, packing 690 million transistors into a tiny 56 mm² die. In contrast, the NVIDIA GeForce GTX 460M uses the older Fermi architecture with the GF106 chip, built on a 40 nm process. This older node results in a much lower transistor density of 4.9 million per square millimeter, yet the chip contains 1,170 million transistors spread across a much larger 238 mm² die.

This manufacturing difference has profound implications. The R5 M320’s smaller, denser chip is far more power-efficient per transistor, though the GTX 460M has a published TDP of 50 W while the R5 M320’s TDP is not listed. The R5 M320 also integrates 320 shading units, compared to the GTX 460M’s 192, giving it a 66.7% advantage in shader count. However, the GTX 460M counters with 32 TMUs and 24 ROPs, versus the R5 M320’s 20 TMUs and 8 ROPs, indicating a different balance of compute versus texture/geometry processing.

Memory technology further separates them. The R5 M320 uses DDR3 memory running at 1000 MHz (2 Gbps effective) on a 64-bit bus, yielding 16.00 GB/s bandwidth. The GTX 460M uses GDDR5 at 625 MHz (2.5 Gbps effective) on a 192-bit bus, yielding 60.00 GB/s—3.75 times more bandwidth. API support also diverges: the R5 M320 supports DirectX 12 (11_1) and Vulkan 1.2.170, while the GTX 460M only reaches DirectX 12 (11_0) and lacks Vulkan support entirely. Both support OpenGL 4.6.

Head-to-Head Benchmarks

The only direct head-to-head benchmark available is Geekbench OpenCL, and the results are decisive. The AMD Radeon R5 M320 scores 5051, while the NVIDIA GeForce GTX 460M scores 4282. This represents an 18% advantage for the AMD chip in this compute-oriented test. This is a substantial margin, suggesting that the R5 M320’s higher shader count and newer architecture provide a significant edge in general-purpose GPU compute tasks.

The average benchmark scores corroborate this trend, with the R5 M320 at 4657 and the GTX 460M at 4282, a gap of 8.8%. Interestingly, the R5 M320’s nearest rival, the AMD Radeon RX 9060 XT 16 GB, has an identical average score of 4657 (0% delta), while the GTX 460M’s closest competitor, the AMD FirePro W2100, scores 4295, just 0.3% higher than the GTX 460M. This places both chips in similar performance tiers, but the R5 M320 sits at the higher end of that tier.

The GTX 460M does not win any head-to-head benchmarks in this dataset. Its only potential advantages lie in specifications like memory bandwidth and texture rate, which are not directly measured in the provided benchmarks. The R5 M320 also holds a slight edge in pixel rate (6.840 GPixel/s vs 5.400 GPixel/s) and a massive lead in FP32 compute (547.2 GFLOPS vs 518.4 GFLOPS), though the texture rate favors the GTX 460M (21.60 GTexel/s vs 17.10 GTexel/s).

FAQ

Q: Which GPU has a higher average benchmark score?

A: The AMD Radeon R5 M320 has an average benchmark score of 4657, which is 8.8% higher than the NVIDIA GeForce GTX 460M’s average score of 4282.

Q: Does the GTX 460M have any specification advantages over the R5 M320?

A: Yes. The GTX 460M has a 192-bit memory bus and 60.00 GB/s bandwidth, versus the R5 M320’s 64-bit bus and 16.00 GB/s. It also has more TMUs (32 vs 20) and ROPs (24 vs 8), plus a higher texture rate of 21.60 GTexel/s.

Q: What is the process node difference between the two chips?

A: The AMD Radeon R5 M320 is manufactured on a 28 nm process at TSMC, while the NVIDIA GeForce GTX 460M uses a 40 nm process, also at TSMC.

Q: Which GPU supports Vulkan?

A: Only the AMD Radeon R5 M320 supports Vulkan, with version 1.2.170. The NVIDIA GeForce GTX 460M does not list Vulkan support in its API specifications.

Q: How do the shading unit counts compare?

A: The AMD Radeon R5 M320 has 320 shading units, which is 66.7% more than the NVIDIA GeForce GTX 460M’s 192 shading units.

Q: What is the memory type and size difference?

A: The R5 M320 uses 4 GB of DDR3 memory, while the GTX 460M uses 1536 MB of GDDR5 memory. The R5 M320 has more total memory but significantly lower bandwidth.

Where Each One Wins

The AMD Radeon R5 M320 wins decisively in raw compute performance, as evidenced by its 18% lead in Geekbench OpenCL and higher FP32 throughput of 547.2 GFLOPS. Its newer GCN architecture also brings modern API support, including Vulkan and DirectX 12 (11_1), making it the better choice for newer software and compute workloads that leverage these interfaces. The larger 4 GB memory pool is another practical win for applications that need to store larger datasets on the GPU.

The NVIDIA GeForce GTX 460M, despite losing the compute battle, wins in memory bandwidth and texture processing. Its 60.00 GB/s bandwidth is 3.75 times that of the R5 M320, which could be a decisive factor in legacy games or applications that are fill-rate limited rather than shader-limited. The higher texture rate of 21.60 GTexel/s and more ROPs (24 vs 8) suggest it may handle texture-heavy scenes or certain older DirectX 11 titles more gracefully. Its PCIe 2.0 x16 interface also offers a wider bus connection than the R5 M320’s PCIe 3.0 x8, though the newer standard partially compensates for the reduced lane count.

Specification Differences

The two GPUs differ across nearly every major specification category. The AMD Radeon R5 M320 features the GCN 1.0 architecture on a 28 nm process, while the NVIDIA GeForce GTX 460M uses the Fermi architecture on a 40 nm process. Transistor counts differ significantly: 690 million for AMD versus 1,170 million for NVIDIA, with die sizes of 56 mm² and 238 mm² respectively. Clock speeds show the R5 M320 with a base of 780 MHz and boost of 855 MHz, while the GTX 460M has no listed base or boost clock, only a memory clock of 625 MHz (2.5 Gbps effective).

Memory configurations are starkly different: the R5 M320 has 4 GB of DDR3 on a 64-bit bus (16.00 GB/s), while the GTX 460M has 1536 MB of GDDR5 on a 192-bit bus (60.00 GB/s). The R5 M320 has 320 shading units, 20 TMUs, and 8 ROPs, versus the GTX 460M’s 192 shading units, 32 TMUs, and 24 ROPs. Pixel rates are 6.840 GPixel/s for AMD and 5.400 GPixel/s for NVIDIA, with texture rates of 17.10 GTexel/s and 21.60 GTexel/s respectively. FP32 performance is 547.2 GFLOPS for AMD and 518.4 GFLOPS for NVIDIA. The R5 M320 is listed as an IGP with no TDP, while the GTX 460M is an MXM module with a 50 W TDP. Bus interfaces are PCIe 3.0 x8 for AMD and PCIe 2.0 x16 for NVIDIA. Finally, the R5 M320 supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170, while the GTX 460M supports DirectX 12 (11_0) and OpenGL 4.6 but no Vulkan.