AMD Radeon R5 M435 vs NVIDIA GeForce 840M Comparison

Head-to-Head Benchmarks

The only direct benchmark comparison recorded in the database is the Geekbench OpenCL test, and the results are extremely close. The AMD Radeon R5 M435 scores 5859 points, while the NVIDIA GeForce 840M scores 5764 points. This gives the AMD part a 1.6% advantage, a margin that is effectively negligible in real-world use. Both chips land in the same performance tier, and the delta is smaller than the typical run-to-run variation you would expect from mobile graphics hardware.

Looking at the broader context, the Radeon R5 M435 sits at the 33rd percentile of all GPUs in the database, while the GeForce 840M sits at the 31st percentile. That two-point gap is consistent with the narrow OpenCL result. The average benchmark score tells a different story, however: the R5 M435 has an average score of 5859 across its recorded tests, while the 840M averages 5322 across two tests. The 840M's average is dragged down by its Geekbench Vulkan score of 4880, a test that the R5 M435 does not have recorded. If you focus only on the shared OpenCL test, the two are nearly identical.

The nearest rival data reinforces how tightly grouped these mobile parts are. The R5 M435 is 0.3% ahead of the AMD Radeon R7 M465, 1.2% behind the Intel UHD Graphics 730, 1.6% behind the AMD Radeon HD 8730M, and 1.6% behind the NVIDIA Quadro K620M. The 840M, meanwhile, is 0.1% ahead of the NVIDIA GeForce 930A, 0.3% ahead of the NVIDIA GeForce GTX 980M, 0.7% ahead of the NVIDIA GeForce 940M, and 0.7% behind the AMD Radeon R7 M445. The 840M's rival list includes the GTX 980M at only 0.3% behind, which seems odd but reflects the fact that the database averages multiple tests, and the 980M's average is pulled down by its own benchmark mix.

In terms of raw compute throughput, the specifications show a clearer separation. The 840M delivers 863.2 GFLOPS of FP32 performance, compared to 659.2 GFLOPS for the R5 M435. That is a 24% theoretical advantage for NVIDIA. The 840M achieves this with 384 shading units running at a base clock of 1029 MHz and a boost clock of 1124 MHz. The R5 M435 has 320 shading units at a base clock of 780 MHz and a boost of 1030 MHz. More shaders and higher clocks add up quickly in compute workloads, even if the OpenCL benchmark does not reflect it.

Texture and pixel throughput go the other way. The R5 M435 has 20 texture mapping units and 8 ROPs, producing a texture rate of 20.60 GTexel/s and a pixel rate of 8.240 GPixel/s. The 840M has 16 TMUs and 8 ROPs, with a texture rate of 17.98 GTexel/s and a pixel rate of 8.992 GPixel/s. So AMD wins texture fill by 14.6%, while NVIDIA wins pixel fill by 9.1%. For games that are texture-bound, the R5 M435 has a slight edge on paper; for fill-rate-bound scenarios, the 840M counters.

Memory bandwidth is where the two diverge most dramatically. The R5 M435 uses 2 GB of GDDR5 on a 64-bit bus, yielding 36.00 GB/s of bandwidth at an effective 4.5 Gbps. The 840M uses 2 GB of DDR3 on the same 64-bit bus, but only achieves 16.02 GB/s at 2 Gbps effective. That is a 124.7% bandwidth advantage for the AMD part. In memory-heavy workloads, such as higher-resolution textures or compute kernels that stream large datasets, this difference can be decisive. The 840M's DDR3 memory is a serious bottleneck, and the data reflects it.

The Verdict

If the only metric is the shared OpenCL benchmark, pick the AMD Radeon R5 M435. It wins the head-to-head test by 1.6%, and it ranks slightly higher in the overall GPU percentile at 33 versus 31 for the 840M. The margin is small enough that most users would never notice it in practice.

If compute throughput matters more to you than the benchmark average, the NVIDIA GeForce 840M is the better part. Its FP32 output of 863.2 GFLOPS is substantially higher than the R5 M435's 659.2 GFLOPS, and it has more shading units at higher clocks. The 840M also supports Vulkan 1.4, while the R5 M435 supports Vulkan 1.2.170, so if you target Vulkan-based applications, the NVIDIA part is the safer choice.

The R5 M435 is the stronger pick for memory-bandwidth-sensitive tasks. Its 36.00 GB/s of GDDR5 bandwidth is more than double the 840M's 16.02 GB/s from DDR3. That advantage shows up in texture-heavy workloads too, where the R5 M435's 20.60 GTexel/s beats the 840M's 17.98 GTexel/s.

Neither card is a performance leader. The R5 M435 sits in the 33rd percentile of all GPUs, and the 840M sits in the 31st. Both are end-of-life mobile parts, released years apart (the 840M in March 2014, the R5 M435 in May 2016), and both are intended for thin-and-light laptops rather than gaming systems. The database shows a statistical tie in the one benchmark they share, with each card winning on the metrics where its architecture is designed to excel.

For the PC builder looking at used laptops, the choice comes down to what you plan to do with the machine. For general OpenCL performance, the R5 M435 edges out the 840M. For raw compute throughput and modern API support, the 840M has the advantage.

Architecture Differences

The AMD Radeon R5 M435 is built on GCN 1.0 architecture, manufactured on a 28 nm process at TSMC. The chip, codenamed Jet, contains 690 million transistors on a die size of 56 mm², giving it a transistor density of 12.3M per mm². It supports DirectX 12 at feature level 11_1, OpenGL 12 (4.6), and Vulkan 1.2.170. The R5 M435 is part of AMD's Gem System (R5 M400) generation, with the predecessor being the Solar System series and the successor being Polaris Mobile.

The NVIDIA GeForce 840M uses Maxwell architecture, also on 28 nm at TSMC. The chip, GM108S, packs 1,020 million transistors on a 77 mm² die, for a transistor density of 13.2M per mm². It supports DirectX 12 at feature level 11_0, OpenGL 4.6, and Vulkan 1.4. The 840M belongs to the GeForce 800M generation, succeeding the GeForce 700M and leading into the GeForce 900M.

The transistor counts reveal a major design difference. The 840M has 1,020 million transistors, nearly 48% more than the R5 M435's 690 million, on a die that is 37.5% larger. This explains the 840M's higher shading unit count and FP32 output. The R5 M435 makes up for its smaller transistor budget with a more efficient memory subsystem and higher texture unit count relative to its transistor budget.

Both chips use a PCIe 3.0 x8 bus interface and are IGP-class parts with portable-device-dependent display outputs. Neither has dimensions listed in the database. The R5 M435 has no recorded TDP, while the 840M is listed at 33 W. The 840M has no power connectors, which is typical for a mobile IGP.

The R5 M435's 320 shading units, 20 TMUs, and 8 ROPs form a configuration that favors texture throughput. The 840M's 384 shading units, 16 TMUs, and 8 ROPs favor compute and pixel throughput. The R5 M435's memory clock of 1125 MHz memory clock produces 4.5 Gbps effective, while the 840M's 1001 MHz memory clock produces 2 Gbps effective. These are the internal frequency differences that drive the bandwidth gap.

The release dates are 2016 for the R5 M435 and 2014 for the 840M, a gap of about two years between the two mobile parts.

The database records the R5 M435 with no FP16 output, and both chips have no RT cores and no tensor cores. Neither lists a game clock or codename beyond what is already noted. The R5 M435's predecessor and successor generations differ, with the 840M having an earlier predecessor (GeForce 700M) and the R5 M435 having an earlier predecessor (Solar System).

FAQ

Q: Which GPU has a higher thermal design power (TDP)?

A: The GeForce 840M has a listed TDP of 33 W. The R5 M435 has no TDP value recorded in the database. The 840M's 33 W figure indicates it is a low-power mobile part designed for thin-and-light laptops.

Q: Which GPU scores higher on Geekbench OpenCL?

A: The R5 M435 scores 5859 points, beating the 840M's 5764 by 1.6%. This is the only head-to-head benchmark test recorded for the R5 M435 in the database.

Q: Does the GeForce 840M have more shading units?**

A: Yes, the 840M has 384 shading units, compared to 320 on the R5 M435. The extra 64 shading units, combined with a higher clock, give the 840M a 24% FP32 throughput advantage at 863.2 GFLOPS versus the R5 M435's 659.2 GFLOPS.

Q: Why does the R5 M435 have higher memory bandwidth than the 840M?

A: The R5 M435 uses GDDR5 memory at 4.5 Gbps effective, delivering 36.00 GB/s on a 64-bit bus. The 840M uses DDR3 at 2 Gbps effective, delivering only 16.02 GB/s on the same 64-bit bus. The GDDR5 type alone explains the more than 2x bandwidth difference.

Q: Which GPU supports a newer version of Vulkan?

A: The 840M supports Vulkan 1.4, while the R5 M435 supports Vulkan 1.2.170. Both support DirectX 12, but the R5 M435 supports feature level 11_1 while the 840M supports 11_0.

Q: What is the transistor count difference between the two?

A: The 840M contains 1,020 million transistors on a 77 mm² die, while the R5 M435 contains 690 million on 56 mm². The 840M has a higher transistor density at 13.2M per mm² versus 12.3M per mm² for the R5 M435.

Where Each One Wins

The AMD Radeon R5 M435 wins the shared OpenCL benchmark, scoring 5859 against the 840M's 5764, a 1.6% lead. It also wins on memory bandwidth at 36.00 GB/s versus the 16.02 GB/s of the 840M, a 124.7% advantage. texture fill rate favors the R5 M435 at 20.60 GTexel/s against the 840M's 17.98 GTexel/s, a 14.6% lead. The R5 M435 supports DirectX feature level 11_1, and it has 20 TMUs to the 840M's 16. The R5 M435 also has a higher GPU percentile at 33 versus the 31st percentile of the 840M.

The NVIDIA GeForce 840M counters with 863.2 GFLOPS of FP32 performance against the 659.2 GFLOPS of the R5 M435, a 24% advantage. The 840M has 384 shading units, 8 ROPs, and a pixel rate of 8.992 GPixel/s versus 8.240 GPixel/s. The 840M's 1,020 million transistors on a 77 mm² die is denser at 13.2M per mm², and it supports Vulkan 1.4. The 840M has a lower TDP of 33 W, and DirectX feature level 11_0.

For compute-intensive applications, the 840M is the better choice. The shader count and clock speed make up for the bandwidth deficit in most real workloads. For memory-heavy applications, the R5 M435 is better suited. The GDDR5 bandwidth advantage of the R5 M435 is hard to ignore.

For texture-heavy workloads, the R5 M435 wins on texture fill rate. For fill-rate-bound work, the 840M edges ahead. For Vulkan-based applications, the 840M wins on API support.

The R5 M435 also wins on transistor efficiency, with its 690 million transistors producing 20.60 GTexel/s of texture throughput. The 840M produces 20 TMUs, which is 25% more than the 840M's 16 TMUs relative to the 840M's 384 shading units, and the 840M achieves 17.98 GTexel/s.

The 840M wins on raw performance per shader, with 863.2 GFLOPS divided by 384 shading units, which is approximately 2.25 GFLOPS per unit, compared to the R5 M435's 659.2 GFLOPS divided by 320 shading units, which is approximately 2.06 GFLOPS per unit, a 9.8% per-shader advantage. This per-shader efficiency is a result of the Maxwell architecture's design.

The R5 M435 wins on texture units per TMU, with 20 TMUs for 690 million, which is 20 TMUs per 690 million, and the 840M has 16 TMUs for 1,020 million, which is 16 per 1,020 million, a 47.8% higher TMU count per transistor for the R5 M435.

Specification Differences

The two GPUs differ on every major specification category except process node, foundry, memory size, bus width, ROP count, slot width, bus interface, and display outputs. Both use 28 nm TSMC, both have 2 GB of memory, both use a 64-bit bus, both have 8 ROPs, both are IGP slot width, both use PCIe 3.0 x8, and both have portable-device-dependent display outputs.

| Specification | AMD Radeon R5 M435 | NVIDIA GeForce 840M |

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

| Architecture | GCN 1.0 | Maxwell |

| Process Node | 28 nm | 28 nm (same |

| Transistors | 690 million | 1,020 million |

| Die Size | 56 mm² | 77 mm² |

| Base Clock | 780 MHz | 1029 MHz |

| Boost Clock | 1030 MHz | 1124 MHz |

| Memory Clock | 1125 MHz, 4.5 Gbps effective | 1001 MHz, 2 Gbps effective |

| Memory Type | GDDR5 | DDR3 |

| Memory Bandwidth | 36.00 GB/s | 16.02 GB/s |

| Shading Units | 320 | 384 |

| TMUs | 20 | 16 |

| Pixel Rate | 8.240 GPixel/s | 8.992 GPixel/s |

| Texture Rate | 20.60 GTexel/s | 17.98 GTexel/s |

| FP32 | 659.2 GFLOPS | 863.2 GFLOPS |

| TDP | Not listed | 33 W |

| Power Connectors | None | No |

| Vulkan | 1.2.170 | 1.4.170 |

| DirectX | 12 (11_1) | 12 (11_0) |

| Vulkan | 1.2.170 | 1.4.170 |

| OpenGL | 4.6 | 4.6 |

| Vulkan | 1.2.170 | 1.4.170 |

The 840M has 33 W TDP, while the R5 M435 has no TDP. The 840M has 1,020 million transistors, the R5 M435 has 690 million. The 840M has 863.2 GFLOPS, the R5 M435 has 659.