AMD Radeon R5 M335 vs NVIDIA GeForce 940MX Comparison

The NVIDIA GeForce 940MX and AMD Radeon R5 M335 are both end-of-life mobile graphics solutions aimed at entry-level laptops, and the benchmark data shows they are extremely close competitors overall. The 940MX averages a benchmark score of 4844, while the R5 M335 trails slightly at 4752, a difference of about 1.9%. Both sit at the 28th percentile among all GPUs, placing them in the same performance tier. The real story here is not about raw speed, which is nearly identical, but about how each card handles different types of workloads and API environments.

Where Each One Wins

The split is clean and directly reflects the two benchmark tests available. The NVIDIA GeForce 940MX takes the Geekbench OpenCL test with a score of 4939, beating the AMD Radeon R5 M335’s 4745 by 4.1%. This is the more significant victory of the two, as OpenCL is a general-purpose compute API used in many productivity and content-creation applications. If your workflow involves GPU-accelerated rendering, filtering, or scientific calculations that rely on OpenCL, the 940MX is the more capable option.

The AMD Radeon R5 M335 wins the Geekbench Vulkan test, but by the narrowest of margins. Its score of 4758 edges out the 940MX’s 4749 by just 0.2%. Vulkan is a low-overhead graphics API increasingly used in modern game engines, so this win, while small, is relevant for gaming. However, a 0.2% difference is effectively a tie in real-world terms. The data suggests that in Vulkan-based scenarios, neither card offers a meaningful advantage, but the R5 M335 technically holds the crown there.

Looking at the broader rival landscape, the 940MX is 0.2% behind the GeForce GTX 560M and 0.5% behind the Radeon R6 M255DX, while being 1.1% ahead of the GeForce RTX 3080 12 GB — an odd comparison that highlights how benchmark averages can cluster tightly. The R5 M335, meanwhile, sits 0.5% ahead of the Radeon R8 M445DX and 1.5% ahead of the Quadro P400, but 0.7% behind the Radeon R5 M255. For practical purposes, both cards are interchangeable in most tasks, but the 940MX is the better pick for compute-heavy OpenCL work, while the R5 M335 has a slight edge in Vulkan gaming.

Architecture Differences

The architectural gap between these two is substantial, even though their performance is similar. The NVIDIA GeForce 940MX is built on the Maxwell architecture using the GM107 chip, manufactured on a 28 nm process at TSMC. It packs 1,870 million transistors into a 148 mm² die, giving a transistor density of 12.6 million per square millimeter. This is a relatively large and complex chip for the entry-level segment.

In contrast, the AMD Radeon R5 M335 uses the GCN 1.0 architecture with the Exo chip, also on a 28 nm process at TSMC. However, it is a much smaller design, with just 690 million transistors on a 56 mm² die and a density of 12.3 million per square millimeter. This means NVIDIA’s chip has roughly 2.7 times more transistors and a die area about 2.6 times larger, yet both deliver comparable frame rates. The efficiency of Maxwell’s design is evident here, as it achieves similar scores with far more hardware resources.

The core configurations diverge significantly. The 940MX has 512 shading units, 32 texture mapping units, and 8 ROPs. The R5 M335 has only 320 shading units and 20 TMUs, but also 8 ROPs. Despite having 60% more shading units and 60% more TMUs, the 940MX’s pixel rate is actually lower at 6.888 GPixel/s versus the R5 M335’s 8.240 GPixel/s. This is a curious anomaly, likely due to clock speed differences. The 940MX’s texture rate is higher at 27.55 GTexel/s compared to 20.60 GTexel/s, and its FP32 compute is 881.7 GFLOPS versus 659.2 GFLOPS, a 33.7% advantage.

Memory is another major differentiator. The 940MX uses 2 GB of GDDR5 on a 64-bit bus, running at 1253 MHz (5 Gbps effective), yielding a bandwidth of 40.10 GB/s. The R5 M335 also has 2 GB on a 64-bit bus, but uses slower DDR3 at 900 MHz (1800 Mbps effective), resulting in just 14.40 GB/s of bandwidth. This is a 2.8x difference in memory bandwidth, which explains why the 940MX performs better in OpenCL, where memory throughput is often the bottleneck. The R5 M335’s higher pixel rate is its only clear architectural win.

FAQ

Q: Which GPU has higher raw compute performance?

A: The NVIDIA GeForce 940MX is decisively ahead in FP32 compute, delivering 881.7 GFLOPS compared to the AMD Radeon R5 M335’s 659.2 GFLOPS, a 33.7% advantage.

Q: Why does the AMD Radeon R5 M335 have a higher pixel rate despite fewer shading units?

A: The R5 M335 achieves 8.240 GPixel/s versus the 940MX’s 6.888 GPixel/s, likely due to different clock behavior. The R5 M335’s clock speeds are not listed, but its pixel rate indicates a higher effective clock in that specific pipeline stage.

Q: Which card has faster memory?

A: The NVIDIA GeForce 940MX. Its GDDR5 memory provides 40.10 GB/s of bandwidth, which is nearly three times the 14.40 GB/s of the Radeon R5 M335’s DDR3.

Q: Are these cards good for modern gaming?

A: Both are at the 28th percentile among all GPUs and are end-of-life products. The 940MX wins the OpenCL test by 4.1%, while the R5 M335 wins Vulkan by 0.2%, but these are entry-level scores that suggest limited capability in demanding modern titles.

Q: What is the difference in DirectX support?

A: The AMD Radeon R5 M335 supports DirectX 12 (11_1), while the NVIDIA GeForce 940MX supports DirectX 12 (11_0). The R5 M335 has a slightly higher feature level.

Q: Which card is more power-efficient?

A: Only the 940MX has a listed TDP of 23 W. The R5 M335’s TDP is not provided in the data, so a direct comparison cannot be made, but the 940MX’s 23 W figure is low for a mobile GPU.

Specification Differences

The two cards differ significantly in nearly every internal specification, despite their similar market positioning.

• Chip: NVIDIA uses GM107, while AMD uses Exo.
• Architecture: NVIDIA is Maxwell; AMD is GCN 1.0.
• Transistors: 1,870 million (NVIDIA) vs 690 million (AMD).
• Die Size: 148 mm² (NVIDIA) vs 56 mm² (AMD).
• Transistor Density: 12.6M / mm² (NVIDIA) vs 12.3M / mm² (AMD).
• Base Clock: 795 MHz (NVIDIA) vs not listed (AMD).
• Boost Clock: 861 MHz (NVIDIA) vs not listed (AMD).
• Memory Clock: 1253 MHz / 5 Gbps effective (NVIDIA) vs 900 MHz / 1800 Mbps effective (AMD).
• Memory Type: GDDR5 (NVIDIA) vs DDR3 (AMD).
• Memory Bandwidth: 40.10 GB/s (NVIDIA) vs 14.40 GB/s (AMD).
• Shading Units: 512 (NVIDIA) vs 320 (AMD).
• TMUs: 32 (NVIDIA) vs 20 (AMD).
• ROPs: 8 (NVIDIA) vs 8 (AMD) — identical.
• Pixel Rate: 6.888 GPixel/s (NVIDIA) vs 8.240 GPixel/s (AMD).
• Texture Rate: 27.55 GTexel/s (NVIDIA) vs 20.60 GTexel/s (AMD).
• FP32: 881.7 GFLOPS (NVIDIA) vs 659.2 GFLOPS (AMD).
• TDP: 23 W (NVIDIA) vs not listed (AMD).
• Vulkan Support: 1.4 (NVIDIA) vs 1.2.170 (AMD).
• Release Date: 2016-06-27 (NVIDIA) vs 2015-10-20 (AMD).

Both cards share the same 28 nm process, TSMC foundry, 2 GB memory size, 64-bit bus width, PCIe 3.0 x8 interface, and DirectX 12 support. They also both lack power connectors and have display outputs described as “Portable Device Dependent.”

Head-to-Head Benchmarks

The two available benchmark tests tell a story of a narrow overall victory for NVIDIA, but with AMD holding its ground in one specific area.

In Geekbench OpenCL, the NVIDIA GeForce 940MX scores 4939 against the AMD Radeon R5 M335’s 4745. This is a 4.1% delta in favor of NVIDIA. This is the more meaningful benchmark for compute workloads, and the 940MX’s superior memory bandwidth (40.10 GB/s vs 14.40 GB/s) is the likely reason. OpenCL tasks often saturate memory, and having nearly three times the bandwidth gives NVIDIA a clear edge. This result aligns with the 940MX’s higher FP32 output of 881.7 GFLOPS versus 659.2 GFLOPS, a 33.7% gap that shows in this workload.

In Geekbench Vulkan, the tables turn, but only barely. The AMD Radeon R5 M335 scores 4758, while the NVIDIA GeForce 940MX scores 4749. The delta is just 0.2% in AMD’s favor. This is within the margin of error for most testing, but it is a win nonetheless. Vulkan’s low-overhead nature may favor the R5 M335’s higher pixel rate (8.240 GPixel/s vs 6.888 GPixel/s), which could help in certain rendering paths. However, a 9-point difference out of roughly 4750 is negligible in practice.

The overall average benchmark scores reflect this split. The 940MX averages 4844, while the R5 M335 averages 4752. This 92-point difference (about 1.9%) is driven entirely by the OpenCL result, since the Vulkan scores are nearly identical. Interestingly, both cards have the GeForce RTX 3080 12 GB as a nearest rival, with the 940MX 1.1% above it and the R5 M335 0.8% below it. This reflects how benchmark averages can flatten out differences between vastly different hardware generations.

The Verdict

The data points to a clear, if modest, overall winner in the NVIDIA GeForce 940MX. Its average benchmark score of 4844 surpasses the Radeon R5 M335’s 4752, and it delivers its win in the more important OpenCL test with a 4.1% margin. For anyone running compute applications, video encoding, or OpenCL-accelerated productivity tools, the 940MX is the better choice. Its 40.10 GB/s of GDDR5 bandwidth and 881.7 GFLOPS of FP32 performance provide a solid foundation for these tasks.

The AMD Radeon R5 M335 is not without merit. Its Vulkan win, though just 0.2%, shows that it can hold its own in modern graphics API scenarios. Its higher pixel rate of 8.240 GPixel/s suggests it may handle certain pixel-bound rendering paths better. However, its DDR3 memory at 14.40 GB/s is a severe bottleneck that limits its overall potential. For gaming, the Vulkan edge is real but so marginal that it will not be perceptible in practice.

The choice comes down to workload. If OpenCL compute is a priority, the 940MX is the obvious pick. If Vulkan gaming is the only concern, the R5 M335 technically wins, but the difference is too small to matter. Since both cards are end-of-life and sit at the 28th percentile, neither is a modern gaming solution. For a practical builder, the 940MX offers better memory, more compute units, and a higher average score. That makes it the safer recommendation for general use, with the R5 M335 reserved for specific Vulkan-oriented scenarios where every point counts.