AMD Radeon R5 M335 vs NVIDIA GeForce GTX 460M Comparison

Head-to-Head Benchmarks

The database records a single direct comparison between these two mobile graphics parts: Geekbench OpenCL. In that test, the AMD Radeon R5 M335 posts a score of 4745, while the NVIDIA GeForce GTX 460M trails at 4282. That is a 10.8% advantage for the AMD chip. This is not a narrow margin; it is a clear, measurable lead in a compute-oriented workload that exercises shading units, memory throughput, and driver overhead.

Context matters here. The AMD R5 M335 sits at the 28th percentile of all GPUs in the database, while the GTX 460M sits at the 25th percentile. The gap between those percentiles is small, yet the actual score difference is meaningful. The AMD part lands 0.5% above the AMD Radeon R8 M445DX (average 4727) and 1.5% above the NVIDIA Quadro P400 (average 4684). The NVIDIA GTX 460M, by contrast, is 0.3% below the AMD FirePro W2100 (average 4295) and 0.3% above the AMD Radeon Vega 3 (average 4268). So the AMD part is competing in a slightly higher tier of the low-end mobile market, while the NVIDIA part sits squarely among entry-level mobile and workstation parts.

Notably, the R5 M335 also has a Geekbench Vulkan score of 4758, which is nearly identical to its OpenCL score. The GTX 460M has no recorded Vulkan score in the database, which is a functional gap given that the R5 M335 supports Vulkan 1.2.170 while the GTX 460M lists Vulkan as null. The single head-to-head benchmark shows the AMD winning outright, with 1 win and 0 losses. The direction of travel is consistent: newer architecture, better compute throughput, and a higher recorded score.

Architecture Differences

The architecture gap here is generational and manufacturing-driven. The AMD Radeon R5 M335 uses the GCN 1.0 architecture on a 28 nm process from TSMC. The chip is codenamed Exo. The GPU packs 690 million transistors onto a 56 mm² die, giving a transistor density of 12.3M per mm². The NVIDIA GeForce GTX 460M uses the Fermi architecture, built on a 40 nm process, also from TSMC, with the GF106 chip. That chip is far larger at 238 mm² and carries 1,170 million transistors, but the older process yields only 4.9M transistors per mm². The AMD design is dramatically more compact and denser.

The memory subsystem differs sharply. The R5 M335 uses 2 GB of DDR3 on a 64 bit bus, running at 900 MHz (1800 Mbps effective), yielding 14.40 GB/s of bandwidth. The GTX 460M uses 1536 MB of GDDR5 on a much wider 192 bit bus, at 625 MHz (2.5 Gbps effective), yielding 60.00 GB/s. That is a 4.2x difference in memory bandwidth in favor of NVIDIA. This is crucial for texture-heavy workloads and higher resolution, but the AMD part compensates with a much newer compute design.

Compute resources differ in scale. The R5 M335 has 320 shading units, 20 TMUs, and 8 ROPs. The GTX 460M has fewer shaders at 192, but more TMUs at 32 and more ROPs at 24. Pixel rate favors the AMD at 8.240 GPixel/s versus 5.400 GPixel/s. Texture rate is close: 20.60 GTexel/s for the AMD, 21.60 GTexel/s for the NVIDIA. The AMD part pulls ahead in FP32 compute at 659.2 GFLOPS versus 518.4 GFLOPS. That is a 27.2% compute advantage for the R5 M335.

The bus interface differs too: PCIe 3.0 x8 on the AMD versus PCIe 2.0 x16 on the NVIDIA. The power story is asymmetric: the NVIDIA has a listed TDP of 50 W and uses an MXM Module slot, while the AMD has no listed TDP and no slot width. Both have no power connectors and portable device dependent display outputs. The AMD was released on 2015-10-20, the NVIDIA on 2010-09-02. That is a five-year gap in release timing, which explains much of the architectural advantage.

Where Each One Wins

The AMD Radeon R5 M335 wins in raw compute and modern API support. Its GCN 1.0 architecture brings DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. The NVIDIA GTX 460M supports DirectX 12 (11_0) and OpenGL 4.6, but has no Vulkan listing. The R5 M335 also wins in the only recorded head-to-head benchmark, and that is the definitive data point. For OpenCL compute tasks, the R5 M335 is 10.8% faster than the GTX 460M, and it lands in a higher percentile among all GPUs.

The GTX 460M, however, retains clear advantages in memory bandwidth. Its 192 bit bus and GDDR5 memory deliver 60.00 GB/s versus 14.40 GB/s for the R5 M335. That is a massive gap that matters for real-world gaming at higher resolutions or with higher texture detail, even if the compute cores are slower. The NVIDIA part also has more ROPs (24 versus 8) and more TMUs (32 versus 20), which can benefit fill-rate-limited scenarios. Its texture rate is slightly higher at 21.60 GTexel/s versus 20.60 GTexel/s. So the GTX 460M is a more balanced fill-rate part, even if its shading is weaker.

In terms of use cases: the R5 M335 is the better choice for OpenCL acceleration, compute workloads, and any Vulkan-dependent application. Its higher FP32 and its modern API support give it a longer software relevance. The GTX 460M is the better choice for memory-bandwidth-heavy tasks, such as large textures or certain image processing filters, though its raw shading power is lower. The GTX 460M's higher pixel rate from its 24 ROPs (5.400 GPixel/s) is still lower than the R5 M335's 8.240 GPixel/s, so the ROP count advantage does not translate to a pixel throughput win.

The data suggests a laptop with the R5 M335 will handle general compute and modern game engines at lower settings. A laptop with the GTX 460M will struggle with modern shader-heavy work but may cope better with bandwidth-limited workloads. The R5 M335's 2 GB memory versus 1536 MB also gives it a capacity edge for larger datasets, despite the slower type.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon R5 M335 has an average score of 4752, while the NVIDIA GTX 460M averages 4282.

Q: What is the biggest single-benchmark difference?

A: In Geekbench OpenCL, the R5 M335 scores 4745 versus 4282 for the GTX 460M, a 10.8% lead for the AMD.

Q: Which GPU has more memory bandwidth?

A: The GTX 460M has 60.00 GB/s bandwidth, which is far higher than the R5 M335's 14.40 GB/s.

Q: Which GPU supports Vulkan?

A: The R5 M335 supports Vulkan 1.2.170. The GTX 460M has no Vulkan listing in the database.

Q: How do their compute capabilities compare?

A: The R5 M335 delivers 659.2 GFLOPS FP32, versus 518.4 GFLOPS for the GTX 460M, a 27.2% advantage for the AMD.

Q: Which has more shading units?

A: The R5 M335 has 320 shading units, while the GTX 460M has 192.

Q: What are the process nodes?

A: The R5 M335 is on 28 nm, the GTX 460M is on 40 nm.

The Verdict

The data points to the AMD Radeon R5 M335 as the better overall part in the recorded benchmarks. It wins the only head-to-head test, has a higher average score (4752 versus 4282), sits at a higher percentile (28th vs 25th), and offers modern API support including Vulkan. Its FP32 compute is higher by 27%, and its transistor density is far superior.

The NVIDIA GTX 460M is not without merit. Its memory bandwidth is 4.2x higher, and it has more ROPs and TMUs. For applications that are purely memory-bound, the GTX 460M could be more responsive. But those are narrow cases. The R5 M335 wins in compute, in the only measured benchmark, and in modern software compatibility. For a user choosing between two end-of-life mobile GPUs, the Radeon is the better pick for compute, general use, and anything that touches OpenCL. The GTX 460M is the pick only if memory bandwidth is the absolute bottleneck, and even then its lower shading power limits its ceiling.

Specification Differences

• Architecture: GCN 1.0 (AMD) vs Fermi (NVIDIA)
• Process node: 28 nm vs 40 nm
• Transistors: 690 million vs 1,170 million
• Die size: 56 mm² vs 238 mm²
• Transistor density: 12.3M / mm² vs 4.9M / mm²
• Memory size: 2 GB vs 1536 MB
• Memory type: DDR3 vs GDDR5
• Bus width: 64 bit vs 192 bit
• Memory clock: 900 MHz / 1800 Mbps effective vs 625 MHz / 2.5 Gbps effective
• Bandwidth: 14.40 GB/s vs 60.00 GB/s
• Shading units: 320 vs 192
• TMUs: 20 vs 32
• ROPs: 8 vs 24
• Pixel rate: 8.240 GPixel/s vs 5.400 GPixel/s
• Texture rate: 20.60 GTexel/s vs 21.60 GTexel/s
• FP32: 659.2 GFLOPS vs 518.4 GFLOPS
• TDP: None listed vs 50 W
• Slot width: None listed vs MXM Module
• Bus interface: PCIe 3.0 x8 vs PCIe 2.0 x16
• DirectX: 12 (11_1) vs 12 (11_0)
• Vulkan: 1.2.170 vs null
• Release date: 2015-10-20 vs 2010-09-02
• Generation: Gem System (R5 M300) vs GeForce 400M
• Predecessor: Solar System vs GeForce 300M
• Successor: Polaris Mobile vs GeForce 500M