AMD Radeon RX 7900 GRE vs NVIDIA GeForce RTX 4080 Mobile Comparison

This comparison pairs two very different products: a mobile GPU designed for laptops and a desktop graphics card. The recorded benchmark data shows the AMD Radeon RX 7900 GRE winning the majority of head-to-head tests, seven out of nine, while the NVIDIA GeForce RTX 4080 Mobile takes two wins, one of them by a very large margin. The database places both GPUs in similar territory overall: the RTX 4080 Mobile sits in the 81st percentile versus all GPUs, the RX 7900 GRE in the 77th, and their average benchmark scores of 38135 and 32456 reflect the specific mix of tests recorded rather than a clean hierarchy.

Head-to-Head Benchmarks

The biggest single result in the entire dataset belongs to the RTX 4080 Mobile: in Geekbench Vulkan it scored 145807 against the RX 7900 GRE's 99850, a 46% lead. That is the standout result for the NVIDIA part and it is not close. If Vulkan is the API that matters for your workload, this is the one number that flips the entire comparison.

Every other test in the recorded data went to AMD. In Geekbench OpenCL the RX 7900 GRE scored 175758 versus 159575, a 9.2% win for the desktop card. The Passmark suite tells a consistent story: g3d went to AMD 27089 to 24926, an 8% gap; GPU compute went to AMD 15016 to 11191, a 25.5% margin; DirectX 9 went AMD's way 310 to 286, 7.7% ahead; DirectX 11 went AMD 300 to 244, an 18.7% gap; and DirectX 12 went AMD 107 to 96, 10.3% ahead. The 2D graphics test also went to AMD, 1180 to 929, a 21.3% difference.

The only other NVIDIA win is Passmark DirectX 10, where the RTX 4080 Mobile scored 157 against 139, a 12.9% lead. That is a legacy API, so its practical weight is limited, but it is a recorded win nonetheless. The overall pattern is clear: AMD wins breadth, NVIDIA wins one very large, very specific Vulkan result plus a legacy API test.

Where Each One Wins

For the RX 7900 GRE, the data points toward general graphics and compute work. The g3d result, the DirectX 9, 11, and 12 results, and the OpenCL result all favor it. The GPU compute margin of 25.5% is the largest compute-side gap in the dataset, and OpenCL at 9.2% ahead reinforces that direction. Anyone running OpenCL-accelerated workloads or playing games through DirectX APIs should expect the RX 7900 GRE to be the faster recorded option.

For the RTX 4080 Mobile, the case is Vulkan. The 46% Geekbench Vulkan lead is enormous and completely out of step with the rest of the results. Engines and applications built on Vulkan represent the one workload category where the recorded data unambiguously favors the NVIDIA mobile part. The DirectX 10 win is also on its side, but that is a dated API.

There is also a form-factor dimension that the data makes explicit. The RTX 4080 Mobile is an integrated mobile part with a 110 W TDP, no power connectors, and portable-device-dependent display outputs. The RX 7900 GRE is a dual-slot desktop card with a 260 W TDP, two 8-pin power connectors, and a suggested 600 W PSU. These two products do not compete for the same physical slot in a build; the benchmark comparison is about performance positioning, not purchase substitution.

Architecture Differences

Both GPUs are built on TSMC's 5 nm process, so node parity is one thing they share. Beyond that, the designs diverge sharply.

The RTX 4080 Mobile uses the AD104 chip on the Ada Lovelace architecture, part of the GeForce 40 Mobile generation, with 35,800 million transistors on a 294 mm² die, giving a density of 121.8M per mm². It has 7424 shading units, 232 TMUs, 80 ROPs, 58 RT cores, and 232 tensor cores. Clocks run from a 1290 MHz base to a 1665 MHz boost. Memory is 12 GB of GDDR6 on a 192-bit bus, delivering 432.0 GB/s of bandwidth at 18 Gbps effective. Theoretical rates are 133.2 GPixel/s pixel fill, 386.3 GTexel/s texture fill, and 24.72 TFLOPS of FP32, with FP16 running at a 1:1 ratio for the same 24.72 TFLOPS.

The RX 7900 GRE uses the Navi 31 chip, codenamed Plum Bonito, on RDNA 3.0, the third Navi generation. It carries far more silicon: 57,700 million transistors on a 529 mm² die, though at a lower density of 109.1M per mm². It has 5120 shading units, 320 TMUs, 160 ROPs, and 80 RT cores, with no tensor cores listed. Its clocking scheme is more aggressive: a 1287 MHz base, a 1880 MHz game clock, and a 2245 MHz boost. Memory is 16 GB of GDDR6 on a wider 256-bit bus, delivering 576.0 GB/s at the same 18 Gbps effective speed. Theoretical throughput is correspondingly higher: 359.2 GPixel/s, 718.4 GTexel/s, and 45.98 TFLOPS FP32, with FP16 at a 2:1 ratio for 91.96 TFLOPS.

The raw spec advantage explains the benchmark pattern. The RX 7900 GRE has roughly double the ROP count, higher clocks, a wider bus, and more memory bandwidth, which shows up as wins across the DirectX tests and compute. The RTX 4080 Mobile counters with tensor cores, which AMD's part lacks in the recorded data, and a higher transistor density. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, Vulkan 1.4, and PCIe 4.0 x16. The RX 7900 GRE also has a recorded 3DMark Steel Nomad DX12 score of 4814; the mobile part has no entry in that test.

The Verdict

The data supports a straightforward split. If the workload is Vulkan-based, the RTX 4080 Mobile's 46% Geekbench Vulkan lead makes it the recorded performance pick, full stop. That single API result is the only category where the mobile part dominates.

For everything else in the database, the RX 7900 GRE is ahead: DirectX 9, 11, and 12, OpenCL, GPU compute, 3D graphics overall, and 2D. Its wins are consistent, sometimes by double-digit margins, and its hardware backing (more ROPs, more bandwidth, more VRAM, higher boost clocks) explains why. The trade-off recorded in the data is power and form factor: 260 W, dual-slot, two 8-pin connectors, and a 600 W PSU recommendation versus a 110 W integrated mobile part. The RX 7900 GRE also has a stated launch MSRP of 549 USD.

Practical read: desktop users running games and compute get the stronger recorded performer in the RX 7900 GRE. Vulkan-focused workloads are the exception, where the RTX 4080 Mobile's result stands alone in the data.

FAQ

Q: Which GPU wins more benchmarks in the recorded data?

A: The RX 7900 GRE wins seven of nine head-to-head tests. The RTX 4080 Mobile wins two.

Q: Where does the RTX 4080 Mobile win decisively?

A: Geekbench Vulkan, scoring 145807 versus 99850, a 46% lead. It also wins Passmark DirectX 10, 157 to 139.

Q: How large is the RX 7900 GRE's biggest win?

A: Passmark GPU compute, 15016 versus 11191, a 25.5% margin for the AMD card.

Q: How do their memory configurations differ?

A: The RTX 4080 Mobile has 12 GB of GDDR6 on a 192-bit bus with 432.0 GB/s of bandwidth. The RX 7900 GRE has 16 GB on a 256-bit bus with 576.0 GB/s. Both run 18 Gbps effective memory.

Q: What is the power situation for each?

A: The RTX 4080 Mobile is a 110 W integrated mobile part with no power connectors. The RX 7900 GRE is a 260 W dual-slot desktop card with two 8-pin connectors and a suggested 600 W PSU.

Q: Do they use the same manufacturing process?

A: Yes, both are built on TSMC 5 nm, but the RX 7900 GRE's die is much larger at 529 mm² versus 294 mm², with 57,700 million transistors versus 35,800 million.

Specification Differences

| Field | RTX 4080 Mobile | RX 7900 GRE |

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

| Chip | AD104 | Navi 31 (Plum Bonito) |

| Architecture | Ada Lovelace | RDNA 3.0 |

| Transistors | 35,800 million | 57,700 million |

| Die size | 294 mm² | 529 mm² |

| Transistor density | 121.8M / mm² | 109.1M / mm² |

| Base clock | 1290 MHz | 1287 MHz |

| Boost clock | 1665 MHz | 2245 MHz |

| Game clock | Not listed | 1880 MHz |

| Memory size | 12 GB GDDR6 | 16 GB GDDR6 |

| Bus width | 192 bit | 256 bit |

| Bandwidth | 432.0 GB/s | 576.0 GB/s |

| Shading units | 7424 | 5120 |

| TMUs | 232 | 320 |

| ROPs | 80 | 160 |

| RT cores | 58 | 80 |

| Tensor cores | 232 | None listed |

| Pixel rate | 133.2 GPixel/s | 359.2 GPixel/s |

| Texture rate | 386.3 GTexel/s | 718.4 GTexel/s |

| FP32 | 24.72 TFLOPS | 45.98 TFLOPS |

| FP16 | 24.72 TFLOPS (1:1) | 91.96 TFLOPS (2:1) |

| TDP | 110 W | 260 W |

| Slot width | IGP | Dual-slot |

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

| Suggested PSU | None listed | 600 W |

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

| Card dimensions | Not listed | 276 x 110 x 51 mm |

| Release date | January 2023 | July 2023 |

| Predecessor | GeForce 30 Mobile | Navi II |

| Successor | GeForce 50 Mobile | Navi IV |

| Percentile vs all GPUs | 81 | 77 |

| Average benchmark score | 38135 | 32456 |