AMD Radeon RX 6700S vs NVIDIA GeForce RTX 3080 Mobile Comparison

The NVIDIA GeForce RTX 3080 Mobile and AMD Radeon RX 6700S are two very different mobile GPU designs separated by a generation and a design philosophy. The data shows a clear overall winner in raw performance, but the AMD part carves out specific niches where its architectural choices pay off. This analysis breaks down their benchmark record, architecture, and practical implications based solely on the provided metrics.

Head-to-Head Benchmarks

The most decisive victory for the NVIDIA GeForce RTX 3080 Mobile comes in the modern 3DMark Steel Nomad DX12 test. Here, the RTX 3080 Mobile scores 2644 against the RX 6700S’s 1451, a massive 82.2% advantage. This is not a small margin; it represents a generational leap in sustained compute under a DirectX 12 workload. The gap is so large that it dwarfs the other differences between the two cards.

Looking at compute-oriented tests, the RTX 3080 Mobile maintains a commanding lead. In Geekbench OpenCL, it scores 104831 versus 70965, a 47.7% delta. The Vulkan result is similarly one-sided, with the NVIDIA part scoring 104066 against AMD’s 76150, a 36.7% advantage. These scores suggest that for general-purpose GPU compute and modern graphics APIs, the Ampere architecture in the 3080 Mobile is significantly more potent than the RDNA 2.0 implementation in the RX 6700S.

The PassMark suite tells a more nuanced story. In DirectX 12, the RTX 3080 Mobile wins with a score of 72 versus 58, a 24.1% margin. The DirectX 11 test shows a closer race, with NVIDIA winning 146 to 134 (a 9% delta). However, the AMD Radeon RX 6700S strikes back in the legacy DirectX 9 test, winning 195 to 170, a -12.8% delta in NVIDIA’s favor (meaning AMD wins by 12.8%). This is a notable reversal, indicating that the AMD card’s driver and hardware handle older, less complex rendering paths more efficiently.

The 3D graphics and compute results confirm the overall trend. In PassMark G3D, the RTX 3080 Mobile scores 16321 versus 15066, an 8.3% win. The PassMark GPU Compute test shows a larger gap, with NVIDIA winning 7276 to 5990, a 21.5% advantage. The only other AMD win comes in the PassMark G2D test, where the RX 6700S scores 739 against NVIDIA’s 637, a 13.8% margin. This 2D performance win is interesting, as it suggests the AMD card’s memory subsystem or driver optimizations favor desktop-style 2D workloads.

The overall scoreboard is lopsided: the RTX 3080 Mobile wins 8 out of 10 head-to-head benchmarks. The AMD card takes the remaining two, which are in older API and 2D tests. The average benchmark scores reflect this, with the RTX 3080 Mobile posting an average of 23628 against the RX 6700S’s 22154. This puts the RTX 3080 Mobile in the 69th percentile of all GPUs, while the RX 6700S sits at the 67th percentile.

Where Each One Wins

The NVIDIA GeForce RTX 3080 Mobile is the clear winner for any modern, demanding workload. Its 82.2% lead in 3DMark Steel Nomad DX12 makes it the superior choice for current-generation AAA games that utilize DirectX 12’s advanced features. Its 47.7% lead in OpenCL and 36.7% lead in Vulkan also make it the stronger option for content creation, machine learning inference, and any application that leverages these APIs for compute acceleration. The data suggests that for 3D rendering, video encoding, and high-fidelity gaming, the RTX 3080 Mobile is in a different performance class.

The AMD Radeon RX 6700S finds its wins in specific, less demanding scenarios. Its victory in PassMark DirectX 9 (195 vs 170) indicates that it handles legacy titles and older game engines with better relative efficiency. This could translate to smoother performance in classic games that don't utilize modern multi-threaded rendering. Similarly, its win in PassMark G2D (739 vs 637) suggests it may have an edge in general desktop usage, 2D applications, and tasks that are not heavily reliant on the 3D pipeline.

Furthermore, the RX 6700S is more efficient in terms of power draw. With a TDP of 80 W versus the RTX 3080 Mobile’s 115 W, it offers a significant portion of the NVIDIA card’s performance (within 8.3% in PassMark G3D) while consuming substantially less power. This makes it a more attractive option for thin-and-light laptops where battery life and thermal management are paramount. The data shows that for a user prioritizing efficiency and legacy game compatibility over raw modern performance, the RX 6700S has a clear use case.

Architecture Differences

The two GPUs are built on fundamentally different architectures and process nodes. The NVIDIA GeForce RTX 3080 Mobile uses the GA104 chip based on the Ampere architecture, fabricated on an 8 nm process at Samsung. This chip houses 17,400 million transistors on a 392 mm² die, resulting in a transistor density of 44.4M per mm². In contrast, the AMD Radeon RX 6700S is built on the Navi 23 chip using the RDNA 2.0 architecture, produced on a more advanced 7 nm process at TSMC. This smaller process allows AMD to fit 11,060 million transistors on a 237 mm² die, achieving a higher transistor density of 46.7M per mm².

The compute resources are starkly different. The RTX 3080 Mobile features 6144 shading units, 192 texture mapping units (TMUs), and 96 ROPs. It also includes 48 dedicated ray tracing cores and 192 tensor cores, which are absent from the RX 6700S. The AMD part has 1792 shading units, 112 TMUs, and 64 ROPs, along with 28 ray accelerators. This massive difference in shading units (6144 vs 1792) is a primary driver of the NVIDIA card’s superior FP32 compute performance, which is rated at 18.98 TFLOPS versus 7.168 TFLOPS for the AMD card.

Clock speeds and memory configuration also differ significantly. The RX 6700S has a much higher base clock of 1700 MHz and boost clock of 2000 MHz, compared to the RTX 3080 Mobile’s 1110 MHz base and 1545 MHz boost. However, the NVIDIA card’s sheer number of cores more than compensates for its lower clocks. Both cards use 8 GB of GDDR6 memory, but the RTX 3080 Mobile has a 256-bit bus providing 448.0 GB/s of bandwidth, while the RX 6700S has a narrower 128-bit bus delivering 224.0 GB/s. This 2x bandwidth advantage is critical for high-resolution textures and compute workloads.

Feature-wise, the RTX 3080 Mobile includes proprietary NVIDIA tensor cores for AI-accelerated features, while the RX 6700S relies on AMD’s RDNA 2.0 feature set. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The RX 6700S has a higher FP16 performance of 14.34 TFLOPS (2:1 ratio) compared to the RTX 3080 Mobile’s 18.98 TFLOPS (1:1 ratio), which means the NVIDIA card’s FP16 throughput is equal to its FP32, whereas AMD’s is halved, but the specifics depend on the workload.

FAQ

Q: Which GPU is faster in modern DirectX 12 games?

A: The NVIDIA GeForce RTX 3080 Mobile is significantly faster. In the 3DMark Steel Nomad DX12 test, it scores 2644 versus the RX 6700S’s 1451, a 82.2% advantage.

Q: Does the AMD Radeon RX 6700S win any benchmarks?

A: Yes. It wins in PassMark DirectX 9 (195 vs 170) and PassMark G2D (739 vs 637), indicating better performance in legacy 3D APIs and 2D desktop workloads.

Q: How large is the performance gap in compute-heavy tasks?

A: The gap is substantial. The RTX 3080 Mobile leads by 47.7% in Geekbench OpenCL and 36.7% in Geekbench Vulkan, making it far better for compute applications.

Q: Is there a significant power consumption difference?

A: Yes. The RTX 3080 Mobile has a TDP of 115 W, while the RX 6700S has a TDP of 80 W. The AMD card achieves this lower power draw while remaining competitive in some tests.

Q: What are the core architecture differences?

A: The RTX 3080 Mobile uses Ampere (GA104) on an 8 nm Samsung process with 6144 shading units and 48 RT cores. The RX 6700S uses RDNA 2.0 (Navi 23) on a 7 nm TSMC process with 1792 shading units and 28 ray accelerators.

Q: Which card has better memory bandwidth?

A: The RTX 3080 Mobile has a 256-bit memory bus offering 448.0 GB/s bandwidth, exactly double the 224.0 GB/s provided by the RX 6700S’s 128-bit bus.

Specification Differences

| Specification | NVIDIA GeForce RTX 3080 Mobile | AMD Radeon RX 6700S |

| :--- | :--- | :--- |

| Architecture | Ampere | RDNA 2.0 |

| Chip | GA104 | Navi 23 |

| Process Node | 8 nm | 7 nm |

| Foundry | Samsung | TSMC |

| Transistors | 17,400 million | 11,060 million |

| Die Size | 392 mm² | 237 mm² |

| Transistor Density | 44.4M / mm² | 46.7M / mm² |

| Base Clock | 1110 MHz | 1700 MHz |

| Boost Clock | 1545 MHz | 2000 MHz |

| Game Clock | N/A | 1890 MHz |

| Memory Bus Width | 256 bit | 128 bit |

| Memory Bandwidth | 448.0 GB/s | 224.0 GB/s |

| Shading Units | 6144 | 1792 |

| TMUs | 192 | 112 |

| ROPs | 96 | 64 |

| RT Cores | 48 | 28 |

| Tensor Cores | 192 | N/A |

| Pixel Rate | 148.3 GPixel/s | 128.0 GPixel/s |

| Texture Rate | 296.6 GTexel/s | 224.0 GTexel/s |

| FP32 Performance | 18.98 TFLOPS | 7.168 TFLOPS |

| FP16 Performance | 18.98 TFLOPS (1:1) | 14.34 TFLOPS (2:1) |

| TDP | 115 W | 80 W |

| Bus Interface | PCIe 4.0 x16 | PCIe 4.0 x8 |

| Release Date | 2021-01-11 | 2022-01-03 |

| Predecessor | GeForce 20 Mobile | Polaris Mobile |

| Percentile (All GPUs) | 69 | 67 |

| Avg Benchmark Score | 23628 | 22154 |