AMD Playstation 5 Pro GPU vs NVIDIA GeForce RTX 5090 SE Comparison

Head-to-Head Benchmarks

The recorded database contains no head-to-head benchmark results for the AMD Playstation 5 Pro GPU and the NVIDIA GeForce RTX 5090 SE, and neither part has an average benchmark score. The comparison must therefore be built on the architectural and specification data available. What the data does show is a stark divide in raw compute capacity. The RTX 5090 SE delivers 66.94 TFLOPS of FP32 throughput, which is 3.7 times the 18.05 TFLOPS of the Playstation 5 Pro GPU. In FP16, the gap narrows in a different way based on ratio definitions. The RTX 5090 SE runs FP16 at a 1:1 ratio with its FP32 rate, holding 66.94 TFLOPS. The Playstation 5 Pro GPU uses a 2:1 FP16 rate, meaning it achieves 36.10 TFLOPS, still substantially lower than the NVIDIA part but much closer than the FP32 comparison.

Pixel throughput tells a similar story. The RTX 5090 SE reaches 380.3 GPixel/s, while the Playstation 5 Pro GPU reaches 150.4 GPixel/s. That is an advantage of roughly 2.5 times for the NVIDIA card. Texture rate is where the gap is most pronounced. The RTX 5090 SE processes 1,045.9 GTexel/s versus 564.0 GTexel/s for the AMD part, a difference of 1.85 times. In every measurable throughput category, the RTX 5090 SE leads decisively. The Playstation 5 Pro GPU counters with a higher base clock of 2170 MHz versus 1740 MHz, and a boost clock of 2350 MHz versus 2377 MHz, putting the two nearly level at peak frequency despite the massive difference in scale.

Memory bandwidth is another area of clear separation. The RTX 5090 SE has 1.34 TB/s of bandwidth, while the Playstation 5 Pro GPU has 576.0 GB/s. The NVIDIA part operates with 24 GB of GDDR7 memory on a 384 bit bus, while the AMD console GPU has 16 GB of GDDR6 on a 256 bit bus. The effective memory clock also differs, 28 Gbps effective for the RTX 5090 SE versus 18 Gbps effective for the Playstation 5 Pro GPU. Every memory metric favors the NVIDIA card by a wide margin.

Neither part has a recorded percentile advantage over the other in the database, as both sit at the 50th percentile against all GPUs and neither has nearest rivals listed. This means the comparison is purely a matter of stated specifications rather than measured outcomes. The data shows a consistent pattern: the RTX 5090 SE dominates in raw throughput, memory capacity, and bandwidth, while the Playstation 5 Pro GPU holds a modest clock advantage and a significantly lower power envelope.

Where Each One Wins

The Playstation 5 Pro GPU wins on operational efficiency in the recorded data. Its 232 W TDP is less than half of the RTX 5090 SE's 500 W. This makes it the appropriate choice for scenarios where power draw is the limiting factor. Its physical footprint is larger, 386 mm in length versus 267 mm, but the console form factor includes integrated housing and cooling. The Playstation 5 Pro GPU also carries a higher base clock, 2170 MHz versus 1740 MHz, which indicates a different operating philosophy, more modest hardware running at higher frequencies.

The RTX 5090 SE wins on every absolute performance metric in the database. It has more shading units, 14,080 versus 3,840, more texture mapping units, 440 versus 240, and more ROPs, 160 versus 64. The NVIDIA card also includes 110 RT cores and 440 tensor cores, features that the Playstation 5 Pro GPU does not list at all. In API support, the RTX 5090 SE supports DirectX 12 Ultimate (12_2) and Vulkan 1.4, while the Playstation 5 Pro GPU lists DirectX as N/A and Vulkan 1.2. The RTX 5090 SE also uses a PCIe 5.0 x16 bus interface, which the console GPU lacks entirely.

Use-case separation follows the specification split. For high-resolution rendering, heavy compute workloads, or applications that leverage ray tracing and tensor operations, the RTX 5090 SE is the only one of the two with the hardware to handle those tasks. For a fixed-power console environment where the entire system must fit within 232 W, the Playstation 5 Pro GPU is the designed solution. Neither part is a substitute for the other in the other's primary domain. The data does not support a direct equivalence claim.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The NVIDIA GeForce RTX 5090 SE delivers 66.94 TFLOPS of FP32 throughput, while the AMD Playstation 5 Pro GPU delivers 18.05 TFLOPS. The NVIDIA part provides 3.7 times the FP32 compute.

Q: How do the memory configurations differ?

A: The Playstation 5 Pro GPU has 16 GB of GDDR6 memory on a 256 bit bus with 576.0 GB/s of bandwidth. The RTX 5090 SE has 24 GB of GDDR7 memory on a 384 bit bus with 1.34 TB/s of bandwidth.

Q: What are the power requirements for each GPU?

A: The Playstation 5 Pro GPU has a TDP of 232 W. The RTX 5090 SE has a TDP of 500 W and a suggested PSU rating of 900 W.

Q: Do both GPUs support ray tracing?

A: The RTX 5090 SE lists 110 RT cores and 440 tensor cores. The Playstation 5 Pro GPU does not list RT core or tensor core counts in the database.

Q: What is the process node for each chip?

A: The Playstation 5 Pro GPU uses a 4 nm process with 21,000 million transistors on a 279 mm² die. The RTX 5090 SE uses a 5 nm process with 92,200 million transistors on a 750 mm² die.

Q: Which GPU has higher clock speeds?

A: The Playstation 5 Pro GPU has a base clock of 2170 MHz and a boost clock of 2350 MHz. The RTX 5090 SE has a base clock of 1740 MHz and a boost clock of 2377 MHz. The AMD part has a higher base clock, while the NVIDIA part has a slightly higher boost clock.

Specification Differences

| Specification | AMD Playstation 5 Pro GPU | NVIDIA GeForce RTX 5090 SE |

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

| Chip | Viola | GB202 |

| Architecture | RDNA 2.0 | Blackwell 2.0 |

| Generation | Console GPU (Sony) | GeForce 50 |

| Process Node | 4 nm | 5 nm |

| Transistors | 21,000 million | 92,200 million |

| Die Size | 279 mm² | 750 mm² |

| Transistor Density | 75.3M / mm² | 122.9M / mm² |

| Base Clock | 2170 MHz | 1740 MHz |

| Boost Clock | 2350 MHz | 2377 MHz |

| Memory Clock | 2250 MHz 18 Gbps effective | 1750 MHz 28 Gbps effective |

| Memory Size | 16 GB | 24 GB |

| Memory Type | GDDR6 | GDDR7 |

| Bus Width | 256 bit | 384 bit |

| Bandwidth | 576.0 GB/s | 1.34 TB/s |

| Shading Units | 3840 | 14080 |

| TMUs | 240 | 440 |

| ROPs | 64 | 160 |

| RT Cores | Not listed | 110 |

| Tensor Cores | Not listed | 440 |

| Pixel Rate | 150.4 GPixel/s | 380.3 GPixel/s |

| Texture Rate | 564.0 GTexel/s | 1,045.9 GTexel/s |

| FP32 | 18.05 TFLOPS | 66.94 TFLOPS |

| FP16 | 36.10 TFLOPS (2:1) | 66.94 TFLOPS (1:1) |

| TDP | 232 W | 500 W |

| Slot Width | Not listed | Dual-slot |

| Power Connectors | Not listed | 1x 16-pin |

| Suggested PSU | Not listed | 900 W |

| Bus Interface | Not listed | PCIe 5.0 x16 |

| Display Outputs | 1x HDMI 2.1, 1x USB Type-C | 1x HDMI 2.1b, 3x DisplayPort 2.1b |

| DirectX | N/A | 12 Ultimate (12_2) |

| Vulkan | 1.2 | 1.4 |

| Length | 386 mm 15.2 inches | 267 mm 10.5 inches |

| Height | 216 mm 8.5 inches | 111 mm 4.4 inches |

| Width | 89 mm 3.5 inches | 40 mm 1.6 inches |

| Release Date | 2024-11-06 | 2025-12-31 |

| Predecessor | Not listed | GeForce 40 |

| Successor | Not listed | GeForce 60 |

| Launch MSRP | 699 USD | 1,499 USD |

Architecture Differences

The architecture gap between these two GPUs is fundamental. The Playstation 5 Pro GPU uses RDNA 2.0, an architecture designed for a fixed-function console environment. The RTX 5090 SE uses Blackwell 2.0, NVIDIA's latest desktop architecture. The process nodes differ as well. The AMD chip is fabricated on a 4 nm process at TSMC, while the NVIDIA chip uses a 5 nm process, also at TSMC. Despite the larger process node, the RTX 5090 SE packs 92,200 million transistors onto a 750 mm² die, compared to 21,000 million transistors on a 279 mm² die for the Playstation 5 Pro GPU. Transistor density is higher on the NVIDIA chip at 122.9M per mm² versus 75.3M per mm².

The compute architecture differs in scale and feature set. The Playstation 5 Pro GPU has 3,840 shading units, 240 TMUs, and 64 ROPs. The RTX 5090 SE has 14,080 shading units, 440 TMUs, and 160 ROPs. The NVIDIA card adds dedicated hardware in the form of 110 RT cores and 440 tensor cores. The Playstation 5 Pro GPU does not list equivalent hardware. This is a structural difference, not a clock speed difference. The NVIDIA part is built to handle ray tracing and tensor workloads directly on dedicated units, while the AMD console GPU relies on its general-purpose shader array.

Memory architecture also diverges. The Playstation 5 Pro GPU uses 16 GB of GDDR6 on a 256 bit bus. The RTX 5090 SE uses 24 GB of GDDR7 on a 384 bit bus. The bandwidth difference, 576.0 GB/s versus 1.34 TB/s, reflects both the wider bus and the faster memory type. API support differs as well. The RTX 5090 SE supports DirectX 12 Ultimate (12_2) and Vulkan 1.4, while the Playstation 5 Pro GPU lists DirectX as N/A and supports Vulkan 1.2. Both support OpenGL 4.6. The NVIDIA card also exposes a PCIe 5.0 x16 interface and a dual-slot form factor with a 16-pin power connector, while the console GPU has no listed bus interface, slot width, or power connector specifications. The display outputs differ, with the console GPU providing one HDMI 2.1 port and one USB Type-C port, and the NVIDIA card providing one HDMI 2.1b port and three DisplayPort 2.1b ports. The release dates place the console GPU in November 2024 and the RTX 5090 SE at the end of December 2025, with the NVIDIA card positioned in the GeForce 50 series between the GeForce 40 and GeForce 60 generations.