AMD Radeon RX 6800 vs NVIDIA GeForce RTX 3080 Ti Mobile Comparison

Head-to-Head Benchmarks

The benchmark data presents a clear overall winner: the AMD Radeon RX 6800 takes 8 of the 10 head-to-head tests, with the NVIDIA GeForce RTX 3080 Ti Mobile winning only 2. The largest single victory belongs to NVIDIA, but the broader pattern heavily favors AMD.

In the 3DMark Steel Nomad DX12 test, the RX 6800 scores 3188 against the RTX 3080 Ti Mobile's 2869, a decisive 11.1% advantage. This is a modern, demanding workload, and the margin is substantial. The Vulkan test shows a similar story: AMD leads with 115107 versus 107502, a 7.1% gap. These two results establish AMD's dominance in current-generation API performance.

The PassMark suite reinforces AMD's lead across legacy and general-purpose workloads. In DirectX 11, the RX 6800 scores 214 versus 164, a dominant 30.5% margin. DirectX 9 shows a 27.9% lead (257 versus 201). The GPU compute test is another strong AMD win: 10864 versus 8471, a 28.2% advantage. The G3D test (22067 versus 19288) yields a 14.4% lead, and even the 2D test (990 versus 818) shows a 21% margin. The DirectX 12 passmark is close, with AMD winning 89 to 88, a slim 1.1% edge.

NVIDIA's two wins are notable for their extremes. The Geekbench OpenCL score is a staggering 117866 for the RTX 3080 Ti Mobile versus 24508 for the RX 6800, a delta of 79.2% in NVIDIA's favor. This is the single largest performance gap in either direction. The other NVIDIA win is marginal: PassMark DirectX 10, 131 versus 128, a 2.3% edge. The OpenCL result suggests a fundamental advantage in compute-heavy OpenCL workloads, while the DirectX 10 win is essentially negligible.

Looking at the average benchmark scores, the RX 6800 records 30095 versus 25740 for the RTX 3080 Ti Mobile. This 4355-point gap aligns with the head-to-head results. The percentile ranks also reflect this: the RX 6800 sits at the 75th percentile of all GPUs, while the RTX 3080 Ti Mobile sits at the 71st percentile. The data shows a consistent, if not uniform, performance advantage for the desktop AMD card.

Architecture Differences

The two GPUs come from fundamentally different design philosophies and process nodes. The AMD Radeon RX 6800 uses the Navi 21 chip built on RDNA 2.0 architecture, manufactured on TSMC's 7 nm process. The NVIDIA GeForce RTX 3080 Ti Mobile uses the GA103 chip on Ampere architecture, built on Samsung's 8 nm process. The node difference is significant: 7 nm versus 8 nm, with different foundries (TSMC versus Samsung).

Transistor counts tell a complex story. The RX 6800 packs 26,800 million transistors on a 520 mm² die, yielding a density of 51.5 million transistors per mm². The RTX 3080 Ti Mobile has 22,000 million transistors on a 496 mm² die, for a density of 44.4 million per mm². AMD has both more transistors and higher density, which partially explains its performance edge in rasterization.

The compute configurations differ sharply. The RX 6800 has 3840 shading units, 240 TMUs, and 96 ROPs. The RTX 3080 Ti Mobile has 7424 shading units, 232 TMUs, and 96 ROPs. NVIDIA has nearly double the shading units, yet this does not translate to superior benchmark results. The RTX 3080 Ti Mobile also includes 58 RT cores and 232 tensor cores, while the RX 6800 has 60 RT cores and no dedicated tensor cores. The AMD card's higher clock speeds are likely a key factor: base 1700 MHz and boost 2105 MHz, versus 810 MHz base and 1260 MHz boost for NVIDIA.

Memory configurations are identical: both have 16 GB of GDDR6 on a 256-bit bus, with 512.0 GB/s bandwidth and 2000 MHz memory clock (16 Gbps effective). The pixel rate favors AMD at 202.1 GPixel/s versus 121.0 GPixel/s, and the texture rate is also higher for AMD at 505.2 GTexel/s versus 292.3 GTexel/s. The FP32 throughput is 16.17 TFLOPS for AMD versus 18.71 TFLOPS for NVIDIA, but FP16 ratios differ: AMD runs FP16 at 32.33 TFLOPS (2:1 ratio), while NVIDIA runs at 18.71 TFLOPS (1:1 ratio).

Power consumption is a major differentiator. The RX 6800 has a TDP of 250 W with dual-slot cooling and 2x 8-pin power connectors, plus a suggested PSU of 600 W. The RTX 3080 Ti Mobile has a TDP of 115 W, no power connectors, and is portable-device dependent. This is a desktop versus mobile comparison, and the power envelope reflects that. The RX 6800 is 267 mm long, 120 mm high, and 40 mm wide. The NVIDIA mobile GPU has no listed dimensions.

Where Each One Wins

The data indicates a clear split between gaming and compute workloads. The AMD Radeon RX 6800 wins in the vast majority of gaming-oriented benchmarks. The 3DMark Steel Nomad DX12 test, the Vulkan test, and all PassMark DirectX tests (9, 10, 11, 12) show AMD ahead, with margins ranging from 1.1% to 30.5%. The G3D and G2D tests also favor AMD. This makes the RX 6800 the stronger choice for DirectX and Vulkan gaming, especially in modern titles that leverage DX12 and Vulkan APIs.

The NVIDIA GeForce RTX 3080 Ti Mobile's wins are concentrated in OpenCL compute and one legacy DirectX test. The Geekbench OpenCL result is extraordinary: 117866 versus 24508, a 79.2% lead. This suggests that for OpenCL-specific compute tasks, such as certain professional applications or scientific workloads, the NVIDIA card is dramatically faster. The DirectX 10 win (131 versus 128) is too small to be meaningful for real-world use.

For compute-heavy workloads using OpenCL, the RTX 3080 Ti Mobile is the clear choice based on the data. For everything else, particularly gaming and general GPU compute via PassMark, the RX 6800 dominates. The PassMark GPU compute test, which measures a broader range of compute tasks, shows AMD ahead by 28.2%, indicating that NVIDIA's OpenCL advantage may be specific to that API rather than general compute performance.

The RX 6800 also wins on efficiency of performance per transistor in many tests, though the power draw is higher. The mobile NVIDIA card's lower TDP (115 W versus 250 W) suggests it is designed for constrained environments, but the benchmark data shows it cannot match the AMD card's throughput in most scenarios despite the lower power requirement.

The Verdict

Based strictly on the recorded benchmark data, the AMD Radeon RX 6800 is the superior performer for the vast majority of use cases. It wins 8 of 10 head-to-head tests, holds a higher average benchmark score (30095 versus 25740), and sits at a higher percentile (75th versus 71st). For gamers and users of DirectX or Vulkan applications, the RX 6800 offers margins that range from a narrow 1.1% in PassMark DX12 to a commanding 30.5% in PassMark DX11. The 3DMark Steel Nomad result, a modern DX12 workload, shows an 11.1% lead that is likely to matter in contemporary titles.

The NVIDIA GeForce RTX 3080 Ti Mobile is the pick only for a narrow but critical niche: OpenCL compute. The 79.2% lead in Geekbench OpenCL is so large that it cannot be ignored for users whose primary workload is OpenCL-based. For those users, the RTX 3080 Ti Mobile is the only rational choice from this data. Its other win, DirectX 10 by 2.3%, is inconsequential.

For a desktop user seeking a general-purpose GPU for gaming and mixed workloads, the RX 6800 is the clear winner. The data shows no scenario, outside of OpenCL, where NVIDIA is competitive. The RX 6800's higher TDP (250 W versus 115 W) is a trade-off for its performance, but the benchmark results justify it. The RTX 3080 Ti Mobile's lower power draw makes it suitable for laptops, but its performance is consistently behind. The verdict is unambiguous: the RX 6800 is the better GPU, with the sole exception of OpenCL-specific tasks.

FAQ

Q: Which GPU wins the most head-to-head benchmarks?

A: The AMD Radeon RX 6800 wins 8 of 10 head-to-head tests, with the NVIDIA GeForce RTX 3080 Ti Mobile winning only 2.

Q: What is the largest performance gap in either direction?

A: The NVIDIA GeForce RTX 3080 Ti Mobile leads in Geekbench OpenCL by 79.2%, scoring 117866 versus 24508 for the AMD Radeon RX 6800.

Q: How do the two GPUs compare in modern DirectX 12 gaming workloads?

A: In 3DMark Steel Nomad DX12, the AMD Radeon RX 6800 scores 3188 versus 2869 for the NVIDIA GeForce RTX 3080 Ti Mobile, an 11.1% advantage. In PassMark DirectX 12, AMD leads 89 to 88.

Q: What are the memory configurations of both GPUs?

A: Both the AMD Radeon RX 6800 and the NVIDIA GeForce RTX 3080 Ti Mobile have 16 GB of GDDR6 memory on a 256-bit bus with 512.0 GB/s bandwidth.

Q: Which GPU has a higher average benchmark score?

A: The AMD Radeon RX 6800 has an average benchmark score of 30095, while the NVIDIA GeForce RTX 3080 Ti Mobile averages 25740.

Q: Is the NVIDIA card better for any specific workload?

A: Yes, the NVIDIA GeForce RTX 3080 Ti Mobile is far ahead in OpenCL compute, with a 79.2% lead in Geekbench OpenCL, but it loses in all other significant tests.

Specification Differences

| Specification | AMD Radeon RX 6800 | NVIDIA GeForce RTX 3080 Ti Mobile |

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

| Architecture | RDNA 2.0 | Ampere |

| Process Node | 7 nm | 8 nm |

| Foundry | TSMC | Samsung |

| Transistors | 26,800 million | 22,000 million |

| Die Size | 520 mm² | 496 mm² |

| Transistor Density | 51.5M / mm² | 44.4M / mm² |

| Base Clock | 1700 MHz | 810 MHz |

| Boost Clock | 2105 MHz | 1260 MHz |

| Shading Units | 3840 | 7424 |

| TMUs | 240 | 232 |

| RT Cores | 60 | 58 |

| Tensor Cores | None | 232 |

| Pixel Rate | 202.1 GPixel/s | 121.0 GPixel/s |

| Texture Rate | 505.2 GTexel/s | 292.3 GTexel/s |

| FP32 | 16.17 TFLOPS | 18.71 TFLOPS |

| FP16 | 32.33 TFLOPS (2:1) | 18.71 TFLOPS (1:1) |

| TDP | 250 W | 115 W |

| Slot Width | Dual-slot | Not specified |

| Power Connectors | 2x 8-pin | None |

| Suggested PSU | 600 W | Not specified |

| Display Outputs | 1x HDMI 2.1, 2x DisplayPort 1.4a, 1x USB Type-C | Portable Device Dependent |

| Release Date | 2020-10-27 | 2022-01-24 |

| Launch MSRP | 579 USD | Not specified |

| Dimensions | 267 mm x 120 mm x 40 mm | Not specified |