AMD Radeon RX 7900 XTX vs NVIDIA GeForce RTX 3080 Mobile Comparison

Where Each One Wins

The benchmark split between the NVIDIA GeForce RTX 3080 Mobile and the AMD Radeon RX 7900 XTX is sharply divided by workload type. The AMD card claims 8 of the 10 recorded head-to-head tests, while the NVIDIA mobile part wins only 2. Those two NVIDIA victories, however, are not minor: they come in compute-oriented and cross-API workloads where the RTX 3080 Mobile demonstrates an unusual strength.

The AMD Radeon RX 7900 XTX dominates the traditional rasterization and DirectX benchmark suite. It wins PassMark DirectX 9, DirectX 10, DirectX 11, and DirectX 12 tests, along with the 2D graphics test, the overall 3D graphics test, and the GPU compute test. The margin in these wins ranges from roughly 28% to 59%, which indicates a consistent and substantial advantage across legacy and modern DirectX paths. The 3DMark Steel Nomad DX12 test, a modern and demanding workload, also goes to AMD by a wide margin.

The NVIDIA GeForce RTX 3080 Mobile takes the Geekbench OpenCL test with a 107.7% delta over the AMD card, meaning it more than doubles the AMD score in that specific compute benchmark. It also wins the Geekbench Vulkan test by 21.6%. These two wins suggest that in certain compute APIs and in Vulkan specifically, the mobile NVIDIA chip punches well above its class. The OpenCL result is particularly striking because the AMD card otherwise leads compute performance in the PassMark GPU compute test by 58.9%.

This split implies that for users running DirectX-based games, the RX 7900 XTX is the clear choice. For workloads that rely on OpenCL or Vulkan, the RTX 3080 Mobile shows competitive or superior performance despite its mobile positioning and lower power envelope. The data does not support a single "best" card; it supports two different cards for two different software ecosystems.

Architecture Differences

The two GPUs come from fundamentally different design philosophies. The NVIDIA GeForce RTX 3080 Mobile uses the GA104 chip built on Ampere architecture, manufactured on an 8 nm process at Samsung. It packs 17,400 million transistors into a 392 mm² die, giving a transistor density of 44.4 million per square millimeter. The AMD Radeon RX 7900 XTX uses the Navi 31 chip (codename Plum Bonito) on RDNA 3.0 architecture, built on a 5 nm process at TSMC. That chip holds 57,700 million transistors across a 529 mm² die, with a density of 109.1 million per square millimeter. The AMD chip is therefore roughly 3.3 times larger in transistor count and over twice as dense.

Memory configurations differ dramatically. The RTX 3080 Mobile has 8 GB of GDDR6 on a 256-bit bus, delivering 448.0 GB/s of bandwidth. The RX 7900 XTX has 24 GB of GDDR6 on a 384-bit bus, delivering 960.0 GB/s. The AMD card triples the capacity and more than doubles the bandwidth. Clock speeds also favor AMD: the RX 7900 XTX runs a base of 1929 MHz, a game clock of 2365 MHz, and a boost of 2498 MHz, while the RTX 3080 Mobile runs a base of 1110 MHz and a boost of 1545 MHz. The AMD memory clock is 2500 MHz (20 Gbps effective) versus 1750 MHz (14 Gbps effective) for NVIDIA.

Both cards have 6144 shading units, but the rest of the compute pipeline diverges. The RX 7900 XTX has 384 texture units and 192 ROPs, while the RTX 3080 Mobile has 192 TMUs and 96 ROPs. The AMD card also has 96 ray accelerators (listed as RT cores) versus 48 for NVIDIA, and no tensor cores, while NVIDIA has 192 tensor cores. Pixel rate is 479.6 GPixel/s for AMD versus 148.3 GPixel/s for NVIDIA, and texture rate is 959.2 GTexel/s versus 296.6 GTexel/s. FP32 throughput is 61.39 TFLOPS for AMD versus 18.98 TFLOPS for NVIDIA, while FP16 is 122.8 TFLOPS (2:1 rate) for AMD versus 18.98 TFLOPS (1:1) for NVIDIA.

Power and physical design are equally divergent. The RTX 3080 Mobile is rated at 115 W TDP with no power connectors, as it is a portable device-dependent part. The RX 7900 XTX is a dual-slot desktop card rated at 355 W TDP, requiring 2x 8-pin power connectors and a suggested 750 W PSU. It measures 287 mm in length, 110 mm in height, and 51 mm in width. The NVIDIA part has no listed dimensions. Both support PCIe 4.0 x16, DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Display outputs differ: the mobile GPU is portable device dependent, while the AMD card offers 1x HDMI 2.1a, 2x DisplayPort 2.1, and 1x USB Type-C.

Head-to-Head Benchmarks

The largest single margin in the dataset belongs to the Geekbench OpenCL test. The RTX 3080 Mobile scores 104831 against 50465 for the RX 7900 XTX, a delta of 107.7% in favor of NVIDIA. This result is anomalous relative to the rest of the data, where AMD leads by wide margins in most tests. It suggests that the OpenCL workload favors NVIDIA's compute stack heavily, or that the mobile part's driver optimizations are particularly strong in this API.

The 3DMark Steel Nomad DX12 test shows the opposite extreme. The RX 7900 XTX scores 6841 versus 2644 for the RTX 3080 Mobile, a 61.4% advantage for AMD. This is the largest AMD win in percentage terms. The PassMark DirectX 11 test is close behind: AMD scores 356 versus 146, a 59% delta. The PassMark GPU compute test shows AMD at 17689 versus 7276, a 58.9% delta. The PassMark G2D test has AMD at 1267 versus 637, a 49.7% delta. The PassMark DirectX 9 test shows 330 versus 170, a 48.5% delta. The PassMark G3D test shows 31238 versus 16321, a 47.8% delta. The PassMark DirectX 12 test shows 131 versus 72, a 45% delta. The PassMark DirectX 10 test shows 166 versus 120, a 27.7% delta.

The Geekbench Vulkan test is the only other NVIDIA win. The RTX 3080 Mobile scores 104066 against 85612 for the RX 7900 XTX, a 21.6% margin. This is a substantial win, though not as dramatic as the OpenCL result. The pattern across the head-to-head data is clear: AMD wins every PassMark subtest and the modern 3DMark test, while NVIDIA wins both Geekbench API tests. The overall benchmark averages reflect this split, with the RTX 3080 Mobile averaging 23628 across all recorded tests and the RX 7900 XTX averaging 19410, despite AMD winning 8 of 10 individual comparisons.

This apparent contradiction, where the card with more wins has a lower average score, is explained by the magnitude of the NVIDIA wins. The OpenCL result alone (104831 versus 50465) adds a massive positive contribution to the NVIDIA average that outweighs the smaller-margin losses in the PassMark suite. The data shows that average scores can be skewed by outlier results, and that individual workload analysis is more informative than a single aggregate number.

The Verdict

The recorded data supports a clear use-case recommendation. The AMD Radeon RX 7900 XTX is the stronger card for DirectX-based gaming and traditional rasterization workloads. It wins all five PassMark DirectX tests (9, 10, 11, 12) and the modern 3DMark Steel Nomad DX12 test by margins ranging from 27.7% to 59%. It also leads the PassMark G3D overall graphics test by 47.8% and the G2D test by 49.7%. For anyone running DirectX games or applications, the RX 7900 XTX is the better choice.

The NVIDIA GeForce RTX 3080 Mobile, despite being a mobile part with a 115 W TDP versus the AMD card's 355 W, wins the Geekbench OpenCL test by 107.7% and the Geekbench Vulkan test by 21.6%. This makes it the better option for OpenCL compute workloads and for Vulkan-based applications. The data does not show why this is the case, but the results are consistent across both Geekbench API tests. Users who rely on OpenCL for compute, or who favor Vulkan as their graphics API, should consider the NVIDIA part.

The percentile rankings place the RTX 3080 Mobile at the 69th percentile of all GPUs, while the RX 7900 XTX sits at the 64th percentile. These rankings reflect the average benchmark scores, not the head-to-head wins, and they highlight the influence of the NVIDIA OpenCL outlier. The nearest rivals for the RTX 3080 Mobile are the GTX TITAN Z (0.5% lower), RTX 3070 Ti Mobile (0.5% higher), RX 9070 (1% lower), and AI PRO R9700 (1.3% higher). The RX 7900 XTX's nearest rivals are the GTX 1060 3 GB (0.4% higher), Quadro K5200 (1% lower), FirePro D300 (1.2% lower), and TITAN Xp (1.2% higher). These rival lists show that the RTX 3080 Mobile competes with modern mid-range and previous-generation high-end cards, while the RX 7900 XTX's average score places it near much older hardware, an artifact of its weak OpenCL showing.

In short: pick the RX 7900 XTX for DirectX gaming and general rasterization, pick the RTX 3080 Mobile for OpenCL compute and Vulkan workloads. The launch MSRP of the RX 7900 XTX is 999 USD.

FAQ

Q: Which card has more memory?

A: The AMD Radeon RX 7900 XTX has 24 GB of GDDR6 on a 384-bit bus with 960.0 GB/s bandwidth. The NVIDIA GeForce RTX 3080 Mobile has 8 GB of GDDR6 on a 256-bit bus with 448.0 GB/s bandwidth.

Q: Why does the RTX 3080 Mobile have a higher average benchmark score than the RX 7900 XTX?

A: The RTX 3080 Mobile averages 23628 across all recorded tests, while the RX 7900 XTX averages 19410. The NVIDIA card's 107.7% win in the Geekbench OpenCL test (104831 versus 50465) skews its average upward, despite losing 8 of 10 head-to-head comparisons.

Q: Which card wins in DirectX 12?

A: The AMD Radeon RX 7900 XTX wins the PassMark DirectX 12 test with a score of 131 versus 72 for the RTX 3080 Mobile, a 45% margin. It also wins the 3DMark Steel Nomad DX12 test with 6841 versus 2644, a 61.4% margin.

Q: What is the power consumption difference?

A: The RTX 3080 Mobile is rated at 115 W TDP with no power connectors. The RX 7900 XTX is rated at 355 W TDP, requires 2x 8-pin power connectors, and has a suggested PSU of 750 W.

Q: Which card wins the Vulkan benchmark?

A: The NVIDIA GeForce RTX 3080 Mobile wins the Geekbench Vulkan test with a score of 104066 versus 85612 for the RX 7900 XTX, a 21.6% margin.

Q: How do the transistor counts compare?

A: The RX 7900 XTX has 57,700 million transistors on a 529 mm² die, while the RTX 3080 Mobile has 17,400 million transistors on a 392 mm² die. The AMD chip is built on a 5 nm process at TSMC, while the NVIDIA chip uses an 8 nm process at Samsung.

Specification Differences

| Specification | NVIDIA GeForce RTX 3080 Mobile | AMD Radeon RX 7900 XTX |

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

| Architecture | Ampere | RDNA 3.0 |

| Process node | 8 nm (Samsung) | 5 nm (TSMC) |

| Transistors | 17,400 million | 57,700 million |

| Die size | 392 mm² | 529 mm² |

| Transistor density | 44.4M / mm² | 109.1M / mm² |

| Base clock | 1110 MHz | 1929 MHz |

| Boost clock | 1545 MHz | 2498 MHz |

| Game clock | N/A | 2365 MHz |

| Memory clock | 1750 MHz (14 Gbps effective) | 2500 MHz (20 Gbps effective) |

| Memory size | 8 GB | 24 GB |

| Memory type | GDDR6 | GDDR6 |

| Memory bus width | 256 bit | 384 bit |

| Memory bandwidth | 448.0 GB/s | 960.0 GB/s |

| TMUs | 192 | 384 |

| ROPs | 96 | 192 |

| RT cores | 48 | 96 |

| Tensor cores | 192 | N/A |

| Pixel rate | 148.3 GPixel/s | 479.6 GPixel/s |

| Texture rate | 296.6 GTexel/s | 959.2 GTexel/s |

| FP32 throughput | 18.98 TFLOPS | 61.39 TFLOPS |

| FP16 throughput | 18.98 TFLOPS (1:1) | 122.8 TFLOPS (2:1) |

| TDP | 115 W | 355 W |

| Slot width | N/A | Dual-slot |

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

| Suggested PSU | N/A | 750 W |

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

| Release date | 2021-01-11 | 2022-11-02 |

| Production status | End-of-life | End-of-life |

| Predecessor | GeForce 20 Mobile | Navi II |

| Successor | N/A | Navi IV |

| Launch MSRP | N/A | 999 USD |