AMD Radeon RX 580 vs NVIDIA RTX PRO 6000D Blackwell Max-Q Comparison

Where Each One Wins

The benchmark data splits these two GPUs into entirely different performance tiers. The AMD Radeon RX 580 wins no head-to-head benchmark in the database. The NVIDIA RTX PRO 6000D Blackwell Max-Q wins every recorded comparison. The most decisive separation appears in DirectX 12 workloads, where the NVIDIA card delivers a 90.9% higher score than the AMD part in the 3DMark Steel Nomad DX12 test.

The RX 580 does retain relevance in legacy API workloads. Its PassMark DirectX 9 score of 124 and PassMark DirectX 10 score of 46 show that older titles remain playable, but these figures do not appear in the head-to-head comparison set. The RX 580's average benchmark score of 12,928 places it at the 53rd percentile of all GPUs, while the RTX PRO 6000D sits at the 50th percentile with an average of 11,088. The percentile difference is misleading here: the RX 580 has 11 recorded benchmarks, while the RTX PRO 6000D has only one, so the percentile positions reflect different sample sizes rather than comparable performance.

For compute-heavy tasks, the RX 580 shows its age. Its Geekbench OpenCL score of 37,453 and Geekbench Vulkan score of 45,173 are respectable for a 2017 part, but the RTX PRO 6000D was not recorded in those same tests. The single overlapping benchmark, 3DMark Steel Nomad DX12, is the only direct comparison available, and it is a landslide.

Architecture Differences

The two GPUs come from different eras and different design philosophies. The RX 580 uses the Polaris 20 chip built on GCN 4.0 architecture, manufactured on a 14 nm process at GlobalFoundries. The RTX PRO 6000D uses the GB202 chip on Blackwell 2.0 architecture, built on a 5 nm process at TSMC. The transistor counts tell the story: 5,700 million for Polaris 20 versus 92,200 million for GB202. Die size grows from 232 mm² to 750 mm², and transistor density jumps from 24.6 million per mm² to 122.9 million per mm².

Shader resources are vastly different. The RX 580 has 2,304 shading units, 144 texture mapping units, and 32 raster output pipelines. The RTX PRO 6000D has 24,064 shading units, 752 TMUs, and 192 ROPs. The NVIDIA part also includes 188 ray tracing cores and 752 tensor cores, features entirely absent from the AMD card. The RX 580 has no RT cores and no tensor cores, so hardware-accelerated ray tracing and AI acceleration are simply not available.

Memory architecture differs completely. The RX 580 uses 8 GB of GDDR5 on a 256-bit bus, delivering 256.0 GB/s of bandwidth. The RTX PRO 6000D uses 96 GB of GDDR7 on a 512-bit bus, delivering 1.79 TB/s of bandwidth. Clock speeds also diverge: the RX 580 runs at a base of 1257 MHz and a boost of 1200 MHz, with memory at 2000 MHz (8 Gbps effective). The RTX PRO 6000D runs at a base of 1590 MHz and a boost of 2288 MHz, with memory at 1750 MHz (28 Gbps effective).

API support follows the generational split. The RX 580 supports DirectX 12 (12_0, OpenGL 4.6, Vulkan 1.3. The RTX PRO 6000D supports DirectX 12 Ultimate (12_2, OpenGL 4.6, Vulkan 1.4. The RX 580 connects via PCIe 3.0 x16, while the RTX PRO 6000D uses PCIe 5.0 x16. Display outputs differ as well: the RX 580 has 1x HDMI 2.0b and 3x DisplayPort 1.4a, while the RTX PRO 6000D has 4x DisplayPort 2.1b.

Head-to-Head Benchmarks

The database contains exactly one head-to-head benchmark between these two GPUs: 3DMark Steel Nomad DX12. The RX 580 scores 1,005, while the RTX PRO 6000D scores 11,088. The delta is negative 90.9% from the AMD card's perspective, meaning the NVIDIA GPU is roughly 11 times faster in this test. This is not a close contest by any measure.

The result is consistent with the architectural gap. The RTX PRO 6000D has more than 10 times the shading units, 5.2 times the TMUs, 6 times the ROPs, and 7 times the memory bandwidth of the RX 580. Its FP32 throughput of 110.1 TFLOPS dwarfs the RX 580's 6.175 TFLOPS, an 17.8-fold difference. Pixel rate is 439.3 GPixel/s versus 42.88 GPixel/s, and texture rate is 1,720.6 GTexel/s versus 193.0 GTexel/s.

The RX 580 does have one area of near parity in its favor. Its PassMark DirectX 11 score of 60 and PassMark DirectX 12 score of 43 are low, but its PassMark G3D score of 8,813 and PassMark GPU Compute score of 3,488 show it can still handle moderate graphical workloads. The RTX PRO 6000D has no recorded scores in those PassMark tests, so no comparison is possible there.

In terms of nearest rivals, the RX 580 sits within 0.6% of the AMD Radeon 740M and the AMD FirePro W5100, and within 0.4% of the NVIDIA GeForce GTX 1660 SUPER. The RTX PRO 6000D sits within 0.4% of the NVIDIA GeForce GTX 1650 SUPER and within 1.2% of the AMD FirePro W4300. These rival relationships suggest that the RX 580 competes with modern integrated graphics and mid-range mobile parts, while the RTX PRO 6000D, despite its massive specifications, is recorded alongside far weaker GPUs in the database's ranking, likely due to the limited benchmark coverage.

FAQ

Q: Which GPU wins in DirectX 12 performance?

A: The NVIDIA RTX PRO 6000D Blackwell Max-Q wins decisively. In the 3DMark Steel Nomad DX12 test, it scores 11,088 versus the RX 580's 1,005, a 90.9% advantage.

Q: Does the RX 580 support ray tracing?

A: No. The RX 580 has no ray tracing cores. The RTX PRO 6000D includes 188 ray tracing cores, so hardware-accelerated ray tracing is exclusive to the NVIDIA part.

Q: How much memory does each GPU have?

A: The RX 580 has 8 GB of GDDR5 on a 256-bit bus. The RTX PRO 6000D has 96 GB of GDDR7 on a 512-bit bus, with 1.79 TB/s of bandwidth compared to 256.0 GB/s.

Q: What is the transistor count difference?

A: The RX 580 has 5,700 million transistors on a 232 mm² die. The RTX PRO 6000D has 92,200 million transistors on a 750 mm² die, built on a denser 5 nm process.

Q: Which GPU has better API support?

A: The RTX PRO 6000D supports DirectX 12 Ultimate (12_2 and Vulkan 1.4. The RX 580 supports DirectX 12 (12_0 and Vulkan 1.3. Both support OpenGL 4.6.

Q: Are there any benchmark tests where the RX 580 wins?

A: In the recorded head-to-head data, the RX 580 wins zero tests. All recorded wins belong to the RTX PRO 6000D. The RX 580's standalone scores in PassMark and Geekbench tests show no overlap with the RTX PRO 6000D's single recorded benchmark.

The Verdict

The data supports a clear conclusion: the NVIDIA RTX PRO 6000D Blackwell Max-Q is the superior GPU in every measurable head-to-head category. The 3DMark Steel Nomad DX12 score of 11,088 versus 1,005 represents a performance gap of an order of magnitude. The RX 580 is an end-of-life product from 2017, built on a 14 nm process with 5,700 million transistors, while the RTX PRO 6000D is an active product from 2025, built on a 5 nm process with 92,200 million transistors. The RTX PRO 6000D offers 96 GB of GDDR7 memory, 188 ray tracing cores, 752 tensor cores, and PCIe 5.0 support. The RX 580 offers 8 GB of GDDR5, no ray tracing cores, no tensor cores, and PCIe 3.0 support.

For workloads that rely on DirectX 12, the RTX PRO 6000D is the only rational choice. For legacy DirectX 9 and DirectX 10 titles, the RX 580 retains some utility, with PassMark scores of 124 and 46 respectively. However, those scores are not compared against the RTX PRO 6000D, which has no recorded data in those tests. The RX 580's average benchmark score of 12,928 is actually higher than the RTX PRO 6000D's 11,088, but this is because the RX 580 has 11 recorded benchmarks across multiple test suites, while the RTX PRO 6000D has only one.

Buyers seeking maximum performance in modern 3D workloads should choose the RTX PRO 6000D. Buyers working with older software that depends on DirectX 9 or DirectX 10, or those constrained by the RX 580's smaller physical footprint (241 mm length versus 267 mm), may find the AMD card sufficient. The RTX PRO 6000D has a higher power draw (300 W versus 185 W) and requires a more substantial power supply (700 W suggested versus 450 W), so system integration costs differ. But in raw benchmark performance, the RTX PRO 6000D is the clear winner.

Specification Differences

| Specification | AMD Radeon RX 580 | NVIDIA RTX PRO 6000D Blackwell Max-Q |

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

| Architecture | GCN 4.0 | Blackwell 2.0 |

| Process Node | 14 nm | 5 nm |

| Foundry | GlobalFoundries | TSMC |

| Transistors | 5,700 million | 92,200 million |

| Die Size | 232 mm² | 750 mm² |

| Transistor Density | 24.6M / mm² | 122.9M / mm² |

| Base Clock | 1257 MHz | 1590 MHz |

| Boost Clock | 1340 MHz | 2288 MHz |

| Memory Size | 8 GB | 96 GB |

| Memory Type | GDDR5 | GDDR7 |

| Memory Bus | 256 bit | 512 bit |

| Memory Bandwidth | 256.0 GB/s | 1.79 TB/s |

| Shading Units | 2304 | 24064 |

| TMUs | 144 | 752 |

| ROPs | 32 | 192 |

| Ray Tracing Cores | None | 188 |

| Tensor Cores | None | 752 |

| Pixel Rate | 42.88 GPixel/s | 439.3 GPixel/s |

| Texture Rate | 193.0 GTexel/s | 1,720.6 GTexel/s |

| FP32 | 6.175 TFLOPS | 110.1 TFLOPS |

| FP16 | 6.175 TFLOPS (1:1) | 110.1 TFLOPS (1:1) |

| TDP | 185 W | 300 W |

| Power Connectors | 1x 8-pin | 1x 16-pin |

| Suggested PSU | 450 W | 700 W |

| Bus Interface | PCIe 3.0 x16 | PCIe 5.0 x16 |

| Display Outputs | 1x HDMI 2.0b, 3x DisplayPort 1.4a | 4x DisplayPort 2.1b |

| DirectX | 12 (12_0) | 12 Ultimate (12_2) |

| Vulkan | 1.3 | 1.4 |

| OpenGL | 4.6 | 4.6 |

| Length | 241 mm (9.5 inches) | 267 mm (10.5 inches) |

| Height | Not specified | 111 mm (4.4 inches) |

| Width | Not specified | 40 mm (1.6 inches) |

| Production Status | End-of-life | Active |

| Release Date | 2017-04-17 | 2025-03-17 |

| Launch MSRP | 229 USD | 8,565 USD |

| Predecessor | Arctic Islands | Workstation Ada |

| Successor | Vega | None |