AMD Radeon RX 6700S vs NVIDIA GeForce RTX 2080 Comparison

The NVIDIA GeForce RTX 2080 and AMD Radeon RX 6700S represent two very different approaches to GPU design: a desktop flagship from the Turing generation and a mobile-focused RDNA 2 part. Benchmark data shows a clear and consistent winner across every single test in the head-to-head comparison, with the RTX 2080 taking all 10 victories. The largest margin comes in Geekbench Vulkan, where the RTX 2080 scores 107797 against the RX 6700S’s 76150, a 41.6% advantage. The smallest gap is in PassMark DirectX 9, where the RTX 2080’s 223 score beats the RX 6700S’s 195 by 14.4%. These results paint a picture of a desktop card that, despite being from an older generation, maintains a commanding lead over a newer mobile chip in raw compute and API-specific workloads.

Head-to-Head Benchmarks

The RTX 2080’s dominance is most pronounced in compute-heavy and modern API tests. In Geekbench OpenCL, the NVIDIA card scores 91313 versus 70965 for the AMD part, a 28.7% delta. This pattern repeats in PassMark GPU Compute, where the RTX 2080’s 7872 score outpaces the RX 6700S’s 5990 by 31.4%. The gap widens further in legacy DirectX 10, with the RTX 2080 scoring 136 against 87, a 56.3% blowout—the single largest percentage difference in the entire dataset. Even in DirectX 12, a modern API where AMD’s RDNA architecture is generally competitive, the RTX 2080 wins 72 to 58, a 24.1% margin.

The 3DMark Steel Nomad DX12 test, a demanding modern benchmark, shows the RTX 2080 ahead at 1752 points versus 1451 for the RX 6700S, a 20.7% advantage. This is notable because it indicates the Turing card’s architectural strengths carry into next-generation workloads. The RX 6700S’s best relative performance comes in DirectX 9, where its 195 score trails by only 14.4%, suggesting that older DX9 titles are the least unfavorable ground for the AMD mobile chip. Across all tests, the RTX 2080’s average benchmark score is 22895, placing it in the 68th percentile of all GPUs, while the RX 6700S averages 22154 and sits at the 67th percentile. The delta between their average scores is just 3.4%, but the per-test breakdown shows the RTX 2080 is consistently ahead rather than relying on a single outlier.

In PassMark G3D, the RTX 2080’s 18720 score beats the RX 6700S’s 15066 by 24.3%, and in PassMark G2D the margin is 22.7% (907 vs 739). The RTX 2080 also wins DirectX 11 by 17.9% (158 vs 134). Interestingly, the nearest rivals data shows both cards are closely matched to their respective peers: the RTX 2080’s closest competitor is the Intel Arc B580 at -0.5%, while the RX 6700S’s nearest rival is the AMD Radeon RX 5700 at -0.1%. This suggests that while the two cards are separated in this head-to-head, each is competitive within its own market segment.

Architecture Differences

The architectural divide here is substantial. The RTX 2080 uses NVIDIA’s Turing architecture on a 12 nm TSMC process, featuring the TU104 chip with 13,600 million transistors on a 545 mm² die. In contrast, the RX 6700S employs AMD’s RDNA 2.0 architecture on a 7 nm TSMC node, using the Navi 23 chip with 11,060 million transistors on a much smaller 237 mm² die. The transistor density tells the story: the RX 6700S packs 46.7 million transistors per mm² versus 25.0M/mm² for the RTX 2080, showing how the newer process allows AMD to cram more into less space.

Core configurations differ dramatically. The RTX 2080 has 2944 shading units, 184 TMUs, and 64 ROPs, while the RX 6700S has 1792 shading units, 112 TMUs, and 64 ROPs. The NVIDIA card also brings 46 RT cores and 368 tensor cores, whereas the AMD part has 28 RT cores and no tensor cores at all. This gives the RTX 2080 a theoretical FP32 throughput of 10.07 TFLOPS versus 7.168 TFLOPS for the RX 6700S, and FP16 of 20.14 TFLOPS versus 14.34 TFLOPS (both at 2:1 ratio). Clock speeds tell a different story: the RX 6700S has a higher base clock at 1700 MHz versus 1515 MHz, and a higher boost at 2000 MHz versus 1710 MHz, with a game clock of 1890 MHz. Despite lower clocks, the RTX 2080’s wider architecture wins.

Memory is another key divergence. Both cards feature 8 GB of GDDR6, but the RTX 2080 uses a 256-bit bus with 448.0 GB/s bandwidth, while the RX 6700S is constrained to a 128-bit bus with just 224.0 GB/s—exactly half the bandwidth. The RTX 2080 also has higher pixel and texture rates at 109.4 GPixel/s and 314.6 GTexel/s versus 128.0 GPixel/s and 224.0 GTexel/s for the AMD card. Power consumption is wildly different: the RTX 2080 is rated at 215 W TDP with a 550 W suggested PSU, while the RX 6700S sips at 80 W TDP with no external power connectors—it’s an IGP-class mobile part. The RTX 2080 is a dual-slot desktop card with 1x 6-pin + 1x 8-pin connectors, while the RX 6700S is a portable-device-dependent IGP.

The Verdict

From the data, the RTX 2080 is the clear performance winner in every measured dimension. Its 10-0 sweep in head-to-head benchmarks, with margins ranging from 14.4% to 56.3%, leaves no ambiguity. This makes sense given its desktop-class power envelope and wider memory bus. However, the RX 6700S is not without merit—it achieves 67th percentile performance (vs 68th for the RTX 2080) while consuming just 80 W, a fraction of the RTX 2080’s 215 W. For a mobile GPU, this is an impressive efficiency figure. The RTX 2080’s nearest rivals (Intel Arc B580 at -0.5%, RX 580 2048SP at -0.7%) show it’s a solid mid-pack performer, while the RX 6700S’s rivals (RX 5700 at -0.1%, RTX 5060 Mobile at -1.3%) indicate it’s equally competitive in its own tier.

The choice comes down to use case. If raw performance in gaming and compute is the priority, the RTX 2080 is the unambiguous pick—it wins every test and offers higher bandwidth, more shading units, and tensor cores for AI workloads. But if the system requires minimal power draw, no external power connectors, and a compact mobile form factor, the RX 6700S delivers 96.7% of the RTX 2080’s average benchmark score (22154 vs 22895) at 37.2% of the power. The RTX 2080 also carries a launch MSRP of 699 USD, while the RX 6700S has no listed MSRP. For desktop builders with power headroom, the RTX 2080 is the better choice. For thin-and-light gaming laptops, the RX 6700S is the only viable option here.

Specification Differences

• Process Node: RTX 2080 uses 12 nm TSMC; RX 6700S uses 7 nm TSMC
• Transistors: RTX 2080 has 13,600 million; RX 6700S has 11,060 million
• Die Size: RTX 2080 is 545 mm²; RX 6700S is 237 mm²
• Transistor Density: RTX 2080 at 25.0M/mm²; RX 6700S at 46.7M/mm²
• Base Clock: RTX 2080 at 1515 MHz; RX 6700S at 1700 MHz
• Boost Clock: RTX 2080 at 1710 MHz; RX 6700S at 2000 MHz
• Shading Units: RTX 2080 has 2944; RX 6700S has 1792
• TMUs: RTX 2080 has 184; RX 6700S has 112
• RT Cores: RTX 2080 has 46; RX 6700S has 28
• Tensor Cores: RTX 2080 has 368; RX 6700S has none
• Memory Bus: RTX 2080 is 256-bit; RX 6700S is 128-bit
• Memory Bandwidth: RTX 2080 at 448.0 GB/s; RX 6700S at 224.0 GB/s
• FP32: RTX 2080 at 10.07 TFLOPS; RX 6700S at 7.168 TFLOPS
• FP16: RTX 2080 at 20.14 TFLOPS; RX 6700S at 14.34 TFLOPS
• Pixel Rate: RTX 2080 at 109.4 GPixel/s; RX 6700S at 128.0 GPixel/s
• Texture Rate: RTX 2080 at 314.6 GTexel/s; RX 6700S at 224.0 GTexel/s
• TDP: RTX 2080 at 215 W; RX 6700S at 80 W
• Power Connectors: RTX 2080 has 1x 6-pin + 1x 8-pin; RX 6700S has none
• Bus Interface: RTX 2080 is PCIe 3.0 x16; RX 6700S is PCIe 4.0 x8
• Slot Width: RTX 2080 is Dual-slot; RX 6700S is IGP
• Display Outputs: RTX 2080 has 1x HDMI 2.0, 3x DisplayPort 1.4a, 1x USB Type-C; RX 6700S is Portable Device Dependent
• Release Date: RTX 2080 on 2018-09-19; RX 6700S on 2022-01-03

FAQ

Q: Which GPU wins in overall benchmark performance?

A: The RTX 2080 wins all 10 head-to-head benchmarks, with an average score of 22895 versus 22154 for the RX 6700S.

Q: What is the largest performance gap between the two cards?

A: The biggest delta is in PassMark DirectX 10, where the RTX 2080 scores 136 versus 87 for the RX 6700S, a 56.3% advantage.

Q: How do their power requirements compare?

A: The RTX 2080 has a 215 W TDP and requires a 550 W suggested PSU with 1x 6-pin + 1x 8-pin connectors, while the RX 6700S has an 80 W TDP with no external power connectors.

Q: Does the RX 6700S have any advantages over the RTX 2080?

A: The RX 6700S has a smaller 7 nm process (vs 12 nm), higher base and boost clocks (1700/2000 MHz vs 1515/1710 MHz), and a higher pixel rate (128.0 GPixel/s vs 109.4 GPixel/s), despite losing in overall performance.

Q: Which card has more memory bandwidth?

A: The RTX 2080 has 448.0 GB/s bandwidth over a 256-bit bus, while the RX 6700S has 224.0 GB/s over a 128-bit bus—exactly half.

Q: Are both cards still in production?

A: No, both are marked as end-of-life. The RTX 2080 released on 2018-09-19 and the RX 6700S on 2022-01-03.