AMD Radeon RX 6800M vs NVIDIA GeForce RTX 2080 SUPER Comparison

FAQ

Q: Which GPU wins in the 3DMark Steel Nomad DX12 test?

A: The AMD Radeon RX 6800M wins with a score of 2238, which is 18.9% ahead of the NVIDIA GeForce RTX 2080 SUPER's score of 1882 in this DirectX 12 workload.

Q: How do the two compare in overall average benchmark score?

A: The AMD Radeon RX 6800M has an average benchmark score of 28874, while the NVIDIA GeForce RTX 2080 SUPER averages 24170. The AMD part sits at the 74th percentile of all GPUs, compared to the NVIDIA card's 69th percentile.

Q: Which GPU has more VRAM, and what is the difference?

A: The AMD Radeon RX 6800M has 12 GB of GDDR6 memory, while the NVIDIA GeForce RTX 2080 SUPER has 8 GB of GDDR6 memory. The AMD GPU also has a 192-bit bus versus the NVIDIA's 256-bit bus.

Q: What is the power draw difference between the two cards?

A: The AMD Radeon RX 6800M has a TDP of 145 W, while the NVIDIA GeForce RTX 2080 SUPER has a TDP of 250 W. The NVIDIA card also requires a 600 W suggested power supply and uses dual-slot cooling with 1x 6-pin and 1x 8-pin connectors.

Q: Which GPU wins in the PassMark G3D benchmark?

A: The NVIDIA GeForce RTX 2080 SUPER wins decisively with a score of 19490, which is 32% higher than the AMD Radeon RX 6800M's score of 13261.

Q: Do both GPUs support the same modern graphics APIs?

A: Yes, both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The AMD card uses RDNA 2.0 architecture, while the NVIDIA card uses Turing architecture.

Architecture Differences

The AMD Radeon RX 6800M is built on the Navi 22 chip using RDNA 2.0 architecture, manufactured on a 7 nm process at TSMC. It contains 17,200 million transistors on a 335 mm² die, giving a transistor density of 51.3M per mm². This is a mobile-oriented design with an IGP slot width and no power connectors, suggesting it is designed for integrated use in laptops.

The NVIDIA GeForce RTX 2080 SUPER uses the TU104 chip with Turing architecture, fabricated on a 12 nm process, also at TSMC. It has 13,600 million transistors on a much larger 545 mm² die, resulting in a lower transistor density of 25.0M per mm². This is a dual-slot desktop card requiring external power connectors.

The AMD GPU features 2560 shading units, 160 texture mapping units, and 64 ROPs, along with 40 ray tracing cores. The NVIDIA GPU has 3072 shading units, 192 TMUs, and 64 ROPs, plus 48 ray tracing cores and 384 tensor cores. The presence of tensor cores on the NVIDIA side indicates support for AI-accelerated features that the AMD card lacks.

Clock speeds differ significantly. The AMD card runs at a base clock of 2116 MHz, a boost clock of 2390 MHz, and a game clock of 2300 MHz. The NVIDIA card operates at a base of 1650 MHz and boost of 1815 MHz. The AMD memory runs at 2000 MHz (16 Gbps effective), while the NVIDIA memory runs at 1937 MHz (15.5 Gbps effective).

The AMD GPU uses PCIe 4.0 x16, while the NVIDIA card uses PCIe 3.0 x16. Display outputs also differ: the AMD card has portable device dependent outputs, while the NVIDIA card provides 1x HDMI 2.0, 3x DisplayPort 1.4a, and 1x USB Type-C.

Head-to-Head Benchmarks

The head-to-head results show a clear split between modern and legacy workloads. In the 3DMark Steel Nomad DX12 test, the AMD Radeon RX 6800M takes a commanding lead. Its score of 2238 is 18.9% higher than the NVIDIA card's 1882. This is the only benchmark where AMD wins, but it is a significant victory in a current-generation DirectX 12 test.

The NVIDIA GeForce RTX 2080 SUPER dominates the remaining nine benchmarks. In Geekbench OpenCL, it scores 99226 versus 87621 for AMD, a delta of -11.7% in favor of NVIDIA. The Geekbench Vulkan test shows an even larger gap: 111284 versus 94766, a 14.8% advantage for NVIDIA.

The PassMark suite reveals substantial NVIDIA superiority across all DirectX versions. In DirectX 10, NVIDIA scores 140 versus 101, a 27.9% lead. DirectX 11 shows 165 versus 127, a 23% advantage. DirectX 12 sees 75 versus 65, a 13.3% edge. DirectX 9 shows the largest percentage gap at 35.2%, with NVIDIA scoring 227 versus AMD's 147.

The compute-oriented tests also favor NVIDIA heavily. PassMark G2D shows 920 versus 538, a 41.5% difference. PassMark G3D gives NVIDIA 19490 versus 13261, a 32% lead. PassMark GPU Compute shows 8290 versus 5032, a 39.3% advantage.

These results indicate that while the AMD card is competitive in modern DirectX 12 workloads, the NVIDIA card maintains a strong edge in legacy APIs and general compute tasks. The data shows NVIDIA winning 9 out of 10 head-to-head comparisons.

Specification Differences

| Specification | AMD Radeon RX 6800M | NVIDIA GeForce RTX 2080 SUPER |

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

| Architecture | RDNA 2.0 | Turing |

| Process Node | 7 nm | 12 nm |

| Transistors | 17,200 million | 13,600 million |

| Die Size | 335 mm² | 545 mm² |

| Transistor Density | 51.3M / mm² | 25.0M / mm² |

| Base Clock | 2116 MHz | 1650 MHz |

| Boost Clock | 2390 MHz | 1815 MHz |

| Memory Clock | 2000 MHz (16 Gbps) | 1937 MHz (15.5 Gbps) |

| Memory Size | 12 GB | 8 GB |

| Memory Bus Width | 192 bit | 256 bit |

| Memory Bandwidth | 384.0 GB/s | 495.9 GB/s |

| Shading Units | 2560 | 3072 |

| TMUs | 160 | 192 |

| ROPs | 64 | 64 |

| Ray Tracing Cores | 40 | 48 |

| Tensor Cores | None | 384 |

| Pixel Rate | 153.0 GPixel/s | 116.2 GPixel/s |

| Texture Rate | 382.4 GTexel/s | 348.5 GTexel/s |

| FP32 | 12.24 TFLOPS | 11.15 TFLOPS |

| FP16 | 24.47 TFLOPS (2:1) | 22.30 TFLOPS (2:1) |

| TDP | 145 W | 250 W |

| Slot Width | IGP | Dual-slot |

| Power Connectors | None | 1x 6-pin + 1x 8-pin |

| Bus Interface | PCIe 4.0 x16 | PCIe 3.0 x16 |

| Release Date | 2021-05-30 | 2019-07-22 |

The Verdict

The benchmark data presents a nuanced picture. The AMD Radeon RX 6800M wins the single most modern test, 3DMark Steel Nomad DX12, with an 18.9% margin. This suggests that in current-generation DirectX 12 games, the AMD architecture has a real advantage. The AMD card also offers more VRAM at 12 GB versus 8 GB, which may benefit texture-heavy workloads.

However, the NVIDIA GeForce RTX 2080 SUPER wins 9 out of 10 head-to-head benchmarks. Its advantages are particularly pronounced in legacy DirectX tests, where it leads by 13.3% to 35.2%. The compute workloads also favor NVIDIA strongly, with a 39.3% lead in GPU compute and a 32% lead in G3D.

The average benchmark scores reflect this split: AMD averages 28874 versus NVIDIA's 24170, but this is driven largely by AMD's strong showing in the Steel Nomad test and the Geekbench Metal result (113721, which is not part of the head-to-head comparison). The percentile rankings put AMD at 74 versus NVIDIA's 69, indicating AMD is generally more competitive across the entire database.

For users prioritizing modern DirectX 12 gaming performance and higher VRAM capacity, the AMD Radeon RX 6800M is the better choice based on the recorded data. For users who need strong performance across a broad range of APIs, particularly legacy DirectX versions and compute workloads, the NVIDIA GeForce RTX 2080 SUPER has a clear advantage.

The power characteristics also matter: AMD's 145 W TDP versus NVIDIA's 250 W TDP means the AMD card is far more efficient in power draw, which is critical for mobile implementations. The NVIDIA card's dual-slot design and power connectors indicate it is intended for desktop use with a substantial power supply.

Ultimately, the choice depends on workload priorities. The data shows AMD winning where it matters most for future-proofing, but NVIDIA dominating the breadth of existing applications.