AMD Radeon R5 M335 vs NVIDIA GeForce GTX 980M Comparison

The Verdict

The NVIDIA GeForce GTX 980M and AMD Radeon R5 M335 occupy completely different tiers of mobile graphics. The data is unambiguous: the GTX 980M dominates every shared benchmark by a massive margin, making it the only choice for gaming or compute-heavy workloads. The R5 M335, by contrast, is a low-end part that should only be considered for basic display output and light, older titles. If you are choosing between these two for a laptop, the GTX 980M is the clear winner unless power draw, physical size, or system integration constraints force the smaller AMD chip. The GTX 980M sits in the 31st percentile of all GPUs, while the R5 M335 lands at the 28th, but that narrow percentile gap does not reflect the chasm in raw performance. The average benchmark score of the GTX 980M is 5308, roughly 11.7% higher than the R5 M335's 4752 average, and in the two directly comparable tests, the NVIDIA part is 402.3% and 272.1% ahead. For any user who needs actual graphics horsepower, the GTX 980M is the only rational pick.

Architecture Differences

The two chips come from different architectural generations and are built around very different design philosophies. The GTX 980M uses the GM204 chip based on Maxwell 2.0 architecture, manufactured by TSMC on a 28 nm process. It packs 5,200 million transistors into a 398 mm² die, giving a transistor density of 13.1 million per square millimeter. The R5 M335 uses the Exo chip based on GCN 1.0, also from TSMC on 28 nm, but with just 690 million transistors on a 56 mm² die, at a density of 12.3 million per square millimeter. The GTX 980M is therefore a much larger, more complex chip with roughly 7.5 times more transistors.

The shader and memory architectures diverge sharply. The GTX 980M has 1536 shading units, 96 texture mapping units, and 64 raster operations pipelines. The R5 M335 has only 320 shading units, 20 TMUs, and 8 ROPs. That is 4.8 times more shaders, 4.8 times more texture units, and 8 times more ROPs on the NVIDIA side. Memory configuration is equally lopsided: the GTX 980M uses 8 GB of GDDR5 on a 256-bit bus with 160.4 GB/s of bandwidth, while the R5 M335 uses 2 GB of DDR3 on a 64-bit bus with just 14.40 GB/s. The memory bandwidth difference is over 11 times in favor of the GTX 980M.

Clock behavior also differs. The GTX 980M has a base clock of 1038 MHz and a boost clock of 1127 MHz, with memory at 1253 MHz (5 Gbps effective). The R5 M335 lists no base or boost clock in the database, but its memory runs at 900 MHz (1800 Mbps effective). API support is near-parity in some areas: both support OpenGL 4.6 and DirectX 12, though the GTX 980M supports DirectX 12 (12_1) while the R5 M335 only supports DirectX 12 (11_1). Vulkan support differs too, with the GTX 980M at Vulkan 1.4 and the R5 M335 at Vulkan 1.2.170. Bus interface is another differentiator: the GTX 980M uses MXM-B (3.0) as an MXM Module, while the R5 M335 connects over PCIe 3.0 x8.

Where Each One Wins

The GTX 980M wins everywhere that performance matters. In the two head-to-head benchmarks recorded, it takes both victories. The Geekbench OpenCL score is 23832 for the GTX 980M versus 4745 for the R5 M335, a 402.3% advantage. The Geekbench Vulkan score is 17703 versus 4758, a 272.1% advantage. The GTX 980M also has additional benchmark data that the R5 M335 lacks entirely: the database shows PassMark scores for the NVIDIA part across DirectX 9, 10, 11, and 12, plus GPU compute and G2D tests. The R5 M335 has no entries for any of those tests, which means there is no recorded evidence of it competing in those workloads at all.

The wins for the R5 M335 are not performance-based. Its advantages are physical and practical: it is a much smaller chip at 56 mm² versus 398 mm², it uses far fewer transistors at 690 million versus 5,200 million, and it has no power connector requirement just like the GTX 980M, but its lower complexity suggests significantly lower power draw. It also uses DDR3 memory, which is cheaper and more common in entry-level laptops. The R5 M335 is a part for basic laptops where the GTX 980M would not fit or would be overkill. In raw compute, rendering, or gaming, the GTX 980M is the only one with meaningful capability.

FAQ

Q: Which GPU is faster in OpenCL compute workloads?

A: The GTX 980M scores 23832 in Geekbench OpenCL, which is 402.3% higher than the R5 M335's 4745. This is a massive gap, over five times the score of the AMD part.

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

A: The GTX 980M scores 17703 in Geekbench Vulkan, beating the R5 M335's 4758 by 272.1%. The NVIDIA chip is nearly four times faster in this API.

Q: Is the R5 M335 suitable for modern gaming?

A: The database shows no gaming or DirectX benchmark scores for the R5 M335, and its only recorded results are 4745 in OpenCL and 4758 in Vulkan. Its 8 ROPs, 20 TMUs, and 14.40 GB/s memory bandwidth indicate it is not built for demanding rendering workloads.

Q: What is the memory configuration difference?

A: The GTX 980M has 8 GB of GDDR5 on a 256-bit bus with 160.4 GB/s bandwidth. The R5 M335 has 2 GB of DDR3 on a 64-bit bus with 14.40 GB/s bandwidth, a bandwidth difference of over 11 times in favor of the NVIDIA part.

Q: Which GPU has better DirectX feature support?

A: The GTX 980M supports DirectX 12 (12_1), while the R5 M335 supports DirectX 12 (11_1). The NVIDIA part has a higher feature level.

Q: Are these GPUs still in production?

A: Both are marked as end-of-life in the database. The GTX 980M was released on 2014-10-06, and the R5 M335 was released on 2015-10-20.

Head-to-Head Benchmarks

The head-to-head data is a two-test affair, and the GTX 980M wins both by enormous margins. The first test is Geekbench OpenCL, where the GTX 980M scores 23832 and the R5 M335 scores 4745. The delta is 402.3%, meaning the NVIDIA part is more than five times faster. This is not a close contest; it is a generational gap compounded by differences in shader count, memory bandwidth, compute units, and chip size.

The second test is Geekbench Vulkan, with the GTX 980M at 17703 and the R5 M335 at 4758. The delta is 272.1%, making the NVIDIA chip nearly four times faster. The GTX 980M's Vulkan score alone dwarfs the AMD part's OpenCL score in the same test, which speaks to how much raw throughput the Maxwell 2.1 chip can deliver.

The GTX 980M also has a broader benchmark footprint in the database: PassMark DirectX 9 at 125, PassMark DirectX 10 at 35, PassMark DirectX 11 at 57, PassMark DirectX 12 at 31, PassMark G2D at 490, PassMark G3D at 7338, PassMark GPU Compute at 2816, 3DMark Steel Nomad DX12 at 649, and Geekbench Vulkan at 17703 and OpenCL at 23832. The R5 M335 has none of these additional results, so there is no recorded evidence of it being competitive in DirectX-era workloads.

The closest rival comparisons in the database show that even the GTX 980M is tightly clustered with other midrange parts: the NVIDIA GeForce 930A is 0.2% below, the GeForce 840M is 0.3% below, the GeForce 940M is 0.5% above, and the AMD Radeon R7 M445 is 0.9% below. The R5 M335's closest rivals are the AMD Radeon R8 M445DX at 0.5% below, the AMD Radeon R5 M255 at 0.7% above, the NVIDIA GeForce RTX 3080 12 GB at 0.8% above, and the NVIDIA Quadro P400 at 1.5% below. These clusters show that the GTX 980M sits near the top of its class, while the R5 M335 sits near the bottom of its own much lower class.

Specification Differences

The specification table below lists only the fields where the two parts differ. The GTX 980M is a high-end mobile chip, and the R5 M335 is a low-end entry part, so the differences are extensive.

| Specification | NVIDIA GeForce GTX 980M | AMD Radeon R5 M335 |

|---|---|---|

| Architecture | Maxwell 2.0 | GCN 1.0 |

| Chip | GM204 | Exo |

| Generation | GeForce 980M | Gem System (R5 M300 (R5 M300) |

| Process Node | 28 nm (TSMC) | 28 nm (TSMC) |

| Transistors | 5,200 million | 690 million |

| Die Size | 398 mm² | 56 mm² |

| Transistor Density | 13.1M / mm² | 12.3M / mm² |

| Memory Size | 8 GB GDDR5 | 2 GB DDR3 DDR3 |

| Memory Bus Width | 256 bit | 256-bit |

| Memory Bandwidth | 160.4 GB/s | 14.4 GB/s |

| Shading Units | 1536 | 320 |

| TMUs | 96 | 20 |

| ROPs | 64 | 8 |

| Pixel Rate | 72.13 GPixel/s | 8.24 GPixel/s |

| Texture Rate | 108.2 GTexel/s | 20.6 GTexel/s |

| FP32 Compute | 3.462 TFLOPS | 659.2 GFLOPS |

| Memory Clock | 1253 MHz (5 Gbps effective) | 900 MHz (1800 Mbps effective) |

| Base Clock | 1038 MHz | N/A |

| Pixel Rate | 72.13 GPixel/s | 8.24 GPixel/s |

| Texture Rate | 108.2 GTexel/s | 20.6 GTexel/s |

| FP32 | 3.462 TFLOPS | 659.2 GFLOPS |

| Vulkan API | Vulkan 1.4 | Vulkan 1.2.170 |

| DirectX API | DirectX 12 (12_1) | DirectX 12 (11_1) |

| Bus Interface | MXM-B (3.0), MXM Module | PCIe 3.0 x8 |

| Release Date | 2014-10-06 | 2015-10-20 |

| Predecessor | GeForce 800M | Solar System |

| Successor | GeForce 10 Mobile | Polaris Mobile |

The GTX 980M has a 256-bit memory bus, while the R5 M335 uses a 64-bit bus. The NVIDIA part has 8 GB GDDR5 versus 2 GB DDR3. The pixel rate is 72.13 GPixel/s versus 8.24 GPixel/s, a difference of roughly 8.8 times. Texture rate is 108.2 GTexel/s versus 20.6 GTexel/s, about 5.3 times higher. FP32 compute is 3.462 TFLOPS versus 659.2 GFLOPS, a 5.3 times difference. The GTX 980M has a base clock of 1038 MHz and boost of 1127 MHz, while the R5 M335 has no listed base or boost clock. The GTX 980M is an MXM module with MXM-B (3.0) interface, while the R5 M335 uses PCIe 3.0 x8. Both have no power connectors, and both are end-of-life. The GTX 980M belongs to the GeForce 900M generation, the R5 M335 to the Gem System (R5 M300) generation. Its predecessor is the GeForce 800M and successor is GeForce 10 Mobile, while the R5 M335's predecessor is Solar System and successor is Polaris Mobile.