AMD Radeon RX 7900 GRE vs NVIDIA GeForce RTX 5080 Mobile Comparison

Head-to-Head Benchmarks

The benchmark data presents a split decision between the NVIDIA GeForce RTX 5080 Mobile and the AMD Radeon RX 7900 GRE. Across the ten recorded tests, the NVIDIA part claims six wins while the AMD card takes four. The margins, however, tell a more nuanced story than the raw win count suggests.

The most dramatic difference appears in the Geekbench Vulkan test. The RTX 5080 Mobile scores 169,754 against 99,850 for the RX 7900 GRE, a decisive 70% advantage. This is the single largest delta in the entire head-to-head set. In contrast, the OpenCL variant of the same benchmark flips the result: the AMD card scores 175,758 versus 166,986, a 5% lead for the RX 7900 GRE. This split between Vulkan and OpenCL performance indicates the NVIDIA architecture has a substantial edge in the Vulkan API path, while AMD retains an advantage in the OpenCL compute path.

In the DirectX legacy tests, the results are mixed. The RTX 5080 Mobile leads in DirectX 10 with a score of 171 versus 139, a 23% margin. In DirectX 9, the NVIDIA part edges ahead by 1.3% (314 versus 310). The DirectX 11 test favors AMD, with the RX 7900 GRE scoring 300 against 253, a 15.7% lead. DirectX 12 swings back to NVIDIA, with the RTX 5080 Mobile posting 116 versus 107, an 8.4% advantage.

The modern 3DMark Steel Nomad DX12 test shows a close contest. The RTX 5080 Mobile scores 4,952 while the RX 7900 GRE scores 4,814, a 2.9% margin for NVIDIA. The PassMark G3D test similarly favors NVIDIA by 2.3% (27,711 versus 27,089). The PassMark G2D test goes to AMD, with the RX 7900 GRE scoring 1,180 versus 1,095, a 7.2% lead.

The compute-focused PassMark GPU Compute test delivers the second-largest margin in the set. The RX 7900 GRE scores 15,016 against 12,134 for the RTX 5080 Mobile, a 19.2% advantage for AMD. This result, combined with the OpenCL lead, suggests the AMD architecture holds a significant edge in general-purpose compute workloads.

Looking at the average benchmark scores, the RTX 5080 Mobile posts an average of 38,349 across all recorded tests, placing it in the 81st percentile of all GPUs in the database. The RX 7900 GRE averages 32,456, landing in the 77th percentile. The nearest rivals for the NVIDIA part include the GeForce MX570 at 38,299 (0.1% delta) and the RTX 4080 Mobile at 38,135 (0.6% delta). For AMD, the closest competitors are the FirePro S10000 at 32,388 (0.2% delta) and the FirePro S9300 X2 at 32,540 (-0.3% delta).

Architecture Differences

The two GPUs come from fundamentally different design philosophies. The RTX 5080 Mobile uses the GB203 chip built on the Blackwell 2.0 architecture, manufactured on a 5 nm process at TSMC. The RX 7900 GRE uses the Navi 31 chip with the RDNA 3.0 architecture, also on a 5 nm TSMC process, with the codename Plum Bonito. Both parts belong to different generations: the NVIDIA card is part of the GeForce 50 Mobile series, while the AMD card is from the Navi III (RX 7000) generation.

The transistor counts differ substantially. The AMD chip packs 57,700 million transistors on a 529 mm² die, while the NVIDIA chip has 45,600 million transistors on a 378 mm² die. This translates to a higher transistor density for NVIDIA at 120.6M per mm² versus 109.1M per mm² for AMD. The larger AMD die allows for more raw compute resources, while the denser NVIDIA design suggests a more compact implementation.

Memory configurations share the same capacity and bus width: both have 16 GB on a 256-bit bus. The memory type differs, with the RTX 5080 Mobile using GDDR7 and the RX 7900 GRE using GDDR6. This results in a significant bandwidth advantage for NVIDIA: 896.0 GB/s versus 576.0 GB/s, a 55.6% higher memory bandwidth for the mobile part.

The compute unit layouts diverge sharply. The RTX 5080 Mobile has 7,680 shading units, 240 TMUs, 96 ROPs, 60 RT cores, and 240 tensor cores. The RX 7900 GRE has 5,120 shading units, 320 TMUs, 160 ROPs, and 80 RT cores, with no tensor cores listed. Despite having fewer shading units, the AMD card achieves higher pixel and texture rates: 359.2 GPixel/s and 718.4 GTexel/s versus 144.0 GPixel/s and 360.0 GTexel/s for NVIDIA. The FP32 throughput also favors AMD at 45.98 TFLOPS versus 23.04 TFLOPS, and the FP16 rate for AMD is 91.96 TFLOPS (2:1 ratio) versus 23.04 TFLOPS (1:1 ratio) for NVIDIA.

Power characteristics could not be more different. The RTX 5080 Mobile is rated at 80 W TDP and is designed as an integrated GPU (IGP) with no power connectors, making it suitable for portable devices. The RX 7900 GRE draws 260 W, requires dual 8-pin power connectors, and is a dual-slot card measuring 276 mm in length. The AMD card also specifies a 600 W suggested PSU, while the NVIDIA part lists none. The bus interface differs as well: PCIe 5.0 x16 for NVIDIA versus PCIe 4.0 x16 for AMD.

FAQ

Q: Which GPU wins more benchmark tests?

A: The NVIDIA GeForce RTX 5080 Mobile wins 6 of the 10 head-to-head tests, while the AMD Radeon RX 7900 GRE wins 4. The NVIDIA part also holds a higher overall percentile rank at 81 versus 77 for AMD.

Q: How large is the performance gap in the Vulkan benchmark?

A: The RTX 5080 Mobile scores 169,754 in Geekbench Vulkan, which is 70% higher than the RX 7900 GRE's score of 99,850. This is the largest margin recorded between the two parts in any test.

Q: Does the AMD card have any clear strengths?

A: Yes. The RX 7900 GRE leads in compute-oriented workloads. It posts a 19.2% advantage in PassMark GPU Compute (15,016 versus 12,134) and a 5% lead in Geekbench OpenCL (175,758 versus 166,986). It also wins in DirectX 11 by 15.7% and in G2D by 7.2%.

Q: What memory specifications do the two cards have?

A: Both have 16 GB on a 256-bit bus. The RTX 5080 Mobile uses GDDR7 with 896.0 GB/s bandwidth, while the RX 7900 GRE uses GDDR6 with 576.0 GB/s bandwidth. The NVIDIA part also runs its memory at 1750 MHz (28 Gbps effective) versus 2250 MHz (18 Gbps effective) for AMD.

Q: How do the power requirements compare?

A: The RTX 5080 Mobile is rated at 80 W TDP and is an integrated GPU with no power connectors. The RX 7900 GRE has a 260 W TDP, requires two 8-pin power connectors, and recommends a 600 W PSU. The AMD card is also a dual-slot design, whereas the NVIDIA part is IGP form factor.

Q: Which card has higher raw compute throughput?

A: The RX 7900 GRE has higher FP32 throughput at 45.98 TFLOPS versus 23.04 TFLOPS for the RTX 5080 Mobile. The AMD card also leads in FP16 at 91.96 TFLOPS (2:1) versus 23.04 TFLOPS (1:1) for NVIDIA.

Specification Differences

| Specification | NVIDIA GeForce RTX 5080 Mobile | AMD Radeon RX 7900 GRE |

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

| Architecture | Blackwell 2.0 | RDNA 3.0 |

| Chip | GB203 | Navi 31 |

| Transistors | 45,600 million | 57,700 million |

| Die Size | 378 mm² | 529 mm² |

| Transistor Density | 120.6M / mm² | 109.1M / mm² |

| Memory Type | GDDR7 | GDDR6 |

| Memory Bandwidth | 896.0 GB/s | 576.0 GB/s |

| Shading Units | 7,680 | 5,120 |

| TMUs | 240 | 320 |

| ROPs | 96 | 160 |

| RT Cores | 60 | 80 |

| Tensor Cores | 240 | None |

| Pixel Rate | 144.0 GPixel/s | 359.2 GPixel/s |

| Texture Rate | 360.0 GTexel/s | 718.4 GTexel/s |

| FP32 | 23.04 TFLOPS | 45.98 TFLOPS |

| FP16 | 23.04 TFLOPS (1:1) | 91.96 TFLOPS (2:1) |

| TDP | 80 W | 260 W |

| Slot Width | IGP | Dual-slot |

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

| Suggested PSU | None | 600 W |

| Bus Interface | PCIe 5.0 x16 | PCIe 4.0 x16 |

| Release Date | 2025-04-01 | 2023-07-26 |

| Launch MSRP | None | 549 USD |

The Verdict

The recorded data draws a clear line between two very different products. The NVIDIA GeForce RTX 5080 Mobile is a low-power integrated solution for portable devices, consuming 80 W with no external power connectors. Despite this constraint, it delivers competitive performance in modern graphics workloads, winning the 3DMark Steel Nomad DX12 test by 2.9% and the Geekbench Vulkan test by a massive 70%. Its GDDR7 memory provides 896.0 GB/s of bandwidth, the highest figure in this comparison.

The AMD Radeon RX 7900 GRE is a high-power desktop card with a 260 W TDP, dual-slot cooling, and dual 8-pin connectors. It excels in compute-heavy scenarios, taking the PassMark GPU Compute test by 19.2% and the Geekbench OpenCL test by 5%. Its raw FP32 throughput of 45.98 TFLOPS is nearly double that of the NVIDIA part, and its pixel and texture rates are substantially higher.

For users selecting a GPU for a portable device where power draw and physical size are critical constraints, the RTX 5080 Mobile is the only viable option in this pair. Its IGP form factor, 80 W TDP, and PCIe 5.0 interface make it suitable for thin-and-light systems. The data shows it holds its own in DirectX 12, Vulkan, and modern 3DMark tests despite its power envelope.

For desktop builders with adequate cooling and power supply headroom, the RX 7900 GRE offers superior compute performance and higher throughput in several legacy DirectX and OpenCL workloads. Its 16 GB GDDR6 memory matches the capacity of the NVIDIA part, though at lower bandwidth. The larger die and higher transistor count support its compute advantage.

The choice comes down to the intended deployment scenario. The benchmark results do not declare a single overall winner; they describe two GPUs optimized for different environments. The RTX 5080 Mobile leads in 6 of 10 tests and ranks in the 81st percentile, while the RX 7900 GRE wins 4 tests and ranks in the 77th percentile. Users prioritizing Vulkan performance and mobile integration should favor NVIDIA. Users prioritizing compute throughput and desktop expansion should favor AMD.