AMD Radeon RX 7900 GRE vs AMD Ryzen Z2 GPU Comparison

Where Each One Wins

The recorded data separates these two AMD parts cleanly by workload class. The Radeon RX 7900 GRE is a discrete desktop graphics card with a full set of benchmark entries across DirectX 9 through 12, OpenCL, Vulkan, and compute workloads. The Ryzen Z2 GPU, by contrast, has no individual benchmark scores recorded in the database, so its wins cannot be measured directly. The comparison therefore rests on architectural and specification differences rather than head-to-head test results.

The RX 7900 GRE posts an average benchmark score of 32456 across its ten recorded tests. Its percentile ranking among all GPUs is 77, meaning it sits above roughly three quarters of the database population. The Ryzen Z2 GPU carries a percentile ranking of 50 but an average benchmark score of zero, since no tests are recorded for it. In terms of measurable wins, the RX 7900 GRE wins every category where data exists: rasterization, ray tracing, compute, and API-specific workloads. The Ryzen Z2 GPU cannot claim a single benchmark win because the database contains no scores for it.

The use-case split is therefore defined by the hardware itself. The RX 7900 GRE delivers 16 GB of GDDR6 memory on a 256 bit bus with 576.0 GB/s of bandwidth, a configuration suited to high resolution rendering and texture-heavy workloads. The Ryzen Z2 GPU pairs 16 GB of LPDDR5X on a 128 bit bus with 119.9 GB/s of bandwidth, a far narrower memory path. The RX 7900 GRE also carries 5120 shading units, 320 texture mapping units, and 160 render output units, while the Ryzen Z2 GPU has 768 shading units, 48 TMUs, and 32 ROPs. Every computational resource is larger on the discrete card.

Architecture Differences

Both parts use the RDNA 3.0 architecture and are manufactured by TSMC, but the process nodes differ. The RX 7900 GRE uses a 5 nm process, while the Ryzen Z2 GPU uses a 4 nm process. The RX 7900 GRE is built on the Navi 31 chip with the codename Plum Bonito and belongs to the Navi III generation of the RX 7000 series. The Ryzen Z2 GPU uses the Hawk Point chip and is classified under the Console GPU generation with no codename or series listed.

Transistor counts and die sizes diverge sharply. The RX 7900 GRE packs 57,700 million transistors on a 529 mm² die, giving a transistor density of 109.1 million per mm². The Ryzen Z2 GPU contains 25,390 million transistors on a 178 mm² die, with a higher density of 142.6 million per mm². The smaller, denser chip reflects the power-constrained target of the Ryzen Z2 GPU, whose TDP is 28 W against the RX 7900 GRE's 260 W.

Memory architecture differs in type and interface. The RX 7900 GRE uses GDDR6 with a 256 bit bus and 576.0 GB/s bandwidth. The Ryzen Z2 GPU uses LPDDR5X with a 128 bit bus and 119.9 GB/s bandwidth. Both have 16 GB capacity, but the bandwidth gap is roughly 4.8 times in favor of the discrete card. Clock behavior also differs: the RX 7900 GRE has a base clock of 1287 MHz, a game clock of 1880 MHz, and a boost clock of 2245 MHz. The Ryzen Z2 GPU has a base clock of 800 MHz and a boost clock of 2700 MHz, with no game clock listed. The higher boost on the smaller chip does not compensate for the far lower resource count.

Ray tracing hardware scales with the rest of the design. The RX 7900 GRE has 80 RT cores, while the Ryzen Z2 GPU has 12. FP32 throughput is 45.98 TFLOPS on the discrete card versus 8.294 TFLOPS on the Ryzen Z2 GPU. FP16 output is 91.96 TFLOPS at 2:1 ratio on the RX 7900 GRE, while the Ryzen Z2 GPU delivers 8.294 TFLOPS at 1:1 ratio, meaning no FP16 acceleration advantage.

Head-to-Head Benchmarks

The database contains no head-to-head benchmark entries for these two products, and the Ryzen Z2 GPU has no individual scores recorded. The comparison must therefore use the RX 7900 GRE's absolute scores and the architectural parameters of the Ryzen Z2 GPU.

The RX 7900 GRE's strongest recorded result is in Geekbench OpenCL with 175758 points. Its Geekbench Vulkan score is 99850. In Passmark tests, the GPU scores 27089 in G3D, 15016 in GPU compute, 1180 in G2D, 310 in DirectX 9, 300 in DirectX 11, 139 in DirectX 10, and 107 in DirectX 12. The 3DMark Steel Nomad DX12 score is 4814. These numbers place the card at the 77th percentile among all GPUs.

Against its nearest rivals in the database, the RX 7900 GRE sits within a tight band. The AMD FirePro S10000 averages 32388, which is 0.2 percent below the RX 7900 GRE. The AMD FirePro S9300 X2 averages 32540, 0.3 percent above. The AMD Radeon RX 590 GME averages 32601, 0.4 percent above. The AMD Radeon Pro 570X averages 32176, 0.9 percent below. The RX 7900 GRE's average of 32456 places it in the middle of this group, with no rival separated by more than one percentage point.

The Ryzen Z2 GPU has no such comparisons available. Its percentile ranking of 50 is a midpoint placement, but without recorded scores the database cannot establish how it performs in any specific workload. The specification sheet indicates a design with 8.294 TFLOPS of FP32, 86.40 GPixel/s pixel rate, and 129.6 GTexel/s texture rate. These figures are far below the RX 7900 GRE's 45.98 TFLOPS, 359.2 GPixel/s, and 718.4 GTexel/s. The discrete card is roughly 5.5 times higher in FP32 throughput, 4.2 times higher in pixel rate, and 5.5 times higher in texture rate.

The Verdict

The data supports only one placement for these two products. The RX 7900 GRE is a high-throughput discrete graphics card with recorded benchmark scores across multiple APIs, a 77th percentile standing, and an average score of 32456. It uses a 260 W power envelope, dual-slot cooling, two 8-pin power connectors, and a 600 W suggested power supply. It is an active production part with a launch MSRP of 549 USD.

The Ryzen Z2 GPU is a 28 W integrated-class chip with no recorded benchmarks, no launch MSRP, no slot width, no power connectors, and no suggested power supply. Its specifications point to a low-power console-oriented design with a single USB Type-C display output. The 16 GB LPDDR5X memory and 128 bit bus give it a fraction of the bandwidth of the discrete card.

From the recorded data, the RX 7900 GRE is the only one of the two that can be evaluated for performance. It wins on every measurable axis: shading units, texture units, ROPs, RT cores, memory bandwidth, pixel rate, texture rate, and FP32 throughput. The Ryzen Z2 GPU's higher boost clock of 2700 MHz and smaller 4 nm process do not offset the resource disparity. The RX 7900 GRE also holds a higher percentile ranking and is the sole product with benchmark evidence in the database.

FAQ

Q: Which GPU has more shading units?

A: The AMD Radeon RX 7900 GRE has 5120 shading units, while the AMD Ryzen Z2 GPU has 768.

Q: What is the memory bandwidth difference?

A: The RX 7900 GRE provides 576.0 GB/s over a 256 bit GDDR6 interface. The Ryzen Z2 GPU provides 119.9 GB/s over a 128 bit LPDDR5X interface.

Q: Do both GPUs use the same architecture?

A: Yes, both use RDNA 3.0. The RX 7900 GRE is built on a 5 nm process with the Navi 31 chip, and the Ryzen Z2 GPU uses a 4 nm process with the Hawk Point chip.

Q: What is the RX 7900 GRE's average benchmark score?

A: The average benchmark score is 32456, with a percentile ranking of 77 among all GPUs.

Q: Does the Ryzen Z2 GPU have any recorded benchmark scores?

A: No. The database lists no benchmark entries for the Ryzen Z2 GPU, and its average benchmark score is zero.

Q: What is the TDP of each GPU?

A: The RX 7900 GRE has a TDP of 260 W and requires two 8-pin power connectors. The Ryzen Z2 GPU has a TDP of 28 W and uses no power connectors.

Specification Differences

| Field | AMD Radeon RX 7900 GRE | AMD Ryzen Z2 GPU |

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

| Chip | Navi 31 | Hawk Point |

| Process node | 5 nm | 4 nm |

| Transistors | 57,700 million | 25,390 million |

| Die size | 529 mm² | 178 mm² |

| Transistor density | 109.1M / mm² | 142.6M / mm² |

| Base clock | 1287 MHz | 800 MHz |

| Boost clock | 2245 MHz | 2700 MHz |

| Game clock | 1880 MHz | None |

| Memory type | GDDR6 | LPDDR5X |

| Memory bus width | 256 bit | 128 bit |

| Memory bandwidth | 576.0 GB/s | 119.9 GB/s |

| Shading units | 5120 | 768 |

| TMUs | 320 | 48 |

| ROPs | 160 | 32 |

| RT cores | 80 | 12 |

| Pixel rate | 359.2 GPixel/s | 86.40 GPixel/s |

| Texture rate | 718.4 GTexel/s | 129.6 GTexel/s |

| FP32 | 45.98 TFLOPS | 8.294 TFLOPS |

| FP16 | 91.96 TFLOPS (2:1) | 8.294 TFLOPS (1:1) |

| TDP | 260 W | 28 W |

| Slot width | Dual-slot | None |

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

| Suggested PSU | 600 W | None |

| Bus interface | PCIe 4.0 x16 | None |

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