AMD Radeon 890M vs NVIDIA RTX PRO 6000 Blackwell Max-Q Comparison

The Verdict

The data is unambiguous: the NVIDIA RTX PRO 6000 Blackwell Max-Q and the AMD Radeon 890M are not competitors in any practical sense. The NVIDIA part wins the only shared benchmark, 3DMark Steel Nomad DX12, by a staggering 1779.3%, scoring 11088 against the AMD’s 590. For any workload that stresses modern DirectX 12 rendering, the choice is the NVIDIA RTX PRO 6000 Blackwell Max-Q, period.

The AMD Radeon 890M is a different class of product entirely. It is an integrated graphics processor (IGP) with a 15 W TDP, designed for portable devices where power draw is the primary constraint. The NVIDIA RTX PRO 6000 Blackwell Max-Q is a 300 W dual-slot workstation card with 96 GB of dedicated GDDR7 memory. The benchmark results show the NVIDIA part is not merely faster, it is in a different performance stratosphere. The data indicates that anyone needing maximum compute and rendering throughput must select the NVIDIA card, while the AMD IGP is only relevant for basic graphics in low-power, portable systems where the NVIDIA card physically cannot be installed.

Architecture Differences

The architectural gap is fundamental. The NVIDIA RTX PRO 6000 Blackwell Max-Q uses the GB202 chip built on Blackwell 2.0 architecture, fabricated on a 5 nm process at TSMC. It packs 92,200 million transistors into a 750 mm² die, with a transistor density of 122.9 million per square millimeter. In contrast, the AMD Radeon 890M uses the Strix Point chip based on RDNA 3.5 architecture, also from TSMC but on a 4 nm node. Its 34,000 million transistors occupy a 233 mm² die, yielding a higher density of 145.9 million per square millimeter, though with far fewer total resources.

The NVIDIA GPU contains 24,064 shading units, 752 texture mapping units, and 192 raster operation units. It also has 188 dedicated ray tracing cores and 752 tensor cores. The AMD IGP has 1,024 shading units, 64 TMUs, and 32 ROPs, plus 16 ray tracing cores but no tensor cores. The NVIDIA part’s compute throughput is listed at 109.7 TFLOPS for both FP32 and FP16, while the AMD part delivers 5.939 TFLOPS for both precisions. The NVIDIA advantage is roughly 18.5 times in raw floating-point throughput. Clock speeds differ accordingly: the NVIDIA base is 1035 MHz with a boost of 2280 MHz, while the AMD base is 400 MHz boosting to 2900 MHz. The AMD’s higher boost clock does not compensate for its far smaller execution engine.

Memory architecture is another stark divider. The NVIDIA RTX PRO 6000 Blackwell Max-Q has 96 GB of GDDR7 across a 512-bit bus, delivering 1.79 TB/s of bandwidth. The AMD Radeon 890M uses system shared memory, with bandwidth listed as system dependent. The NVIDIA card uses a PCIe 5.0 x16 interface, while the AMD IGP uses PCIe 4.0 x8. Display outputs also differ: the NVIDIA card has 4x DisplayPort 2.1b, while the AMD is portable device dependent. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API compatibility is not a differentiator.

FAQ

Q: Which GPU is faster in 3DMark Steel Nomad DX12?

A: The NVIDIA RTX PRO 6000 Blackwell Max-Q scores 11088, which is 1779.3% higher than the AMD Radeon 890M’s 590 in that specific test.

Q: What is the TDP difference between these two?

A: The NVIDIA RTX PRO 6000 Blackwell Max-Q has a 300 W TDP, while the AMD Radeon 890M is rated at 15 W. That is a 20 times difference in power draw.

Q: How much memory does each GPU have?

A: The NVIDIA RTX PRO 6000 Blackwell Max-Q has 96 GB of dedicated GDDR7 memory. The AMD Radeon 890M uses system shared memory, with no dedicated VRAM of its own.

Q: Do both cards support ray tracing?

A: Yes, both have ray tracing cores. The NVIDIA part has 188 RT cores, while the AMD part has 16. However, the NVIDIA card’s RT core count is 11.75 times higher.

Q: Which GPU has a higher transistor density?

A: The AMD Radeon 890M has a higher density at 145.9 million transistors per mm², compared to the NVIDIA RTX PRO 6000 Blackwell Max-Q’s 122.9 million per mm². But the NVIDIA chip has far more total transistors at 92,200 million versus 34,000 million.

Q: What is the launch date for each product?

A: The AMD Radeon 890M was released on 2024-07-14, and the NVIDIA RTX PRO 6000 Blackwell Max-Q followed on 2025-03-17.

Specification Differences

| Specification | NVIDIA RTX PRO 6000 Blackwell Max-Q | AMD Radeon 890M |

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

| Architecture | Blackwell 2.0 | RDNA 3.5 |

| Process Node | 5 nm | 4 nm |

| Transistors | 92,200 million | 34,000 million |

| Die Size | 750 mm² | 233 mm² |

| Transistor Density | 122.9M / mm² | 145.9M / mm² |

| Base Clock | 1035 MHz | 400 MHz |

| Boost Clock | 2280 MHz | 2900 MHz |

| Memory Size | 96 GB | System Shared |

| Memory Type | GDDR7 | System Shared |

| Memory Bus Width | 512 bit | System Shared |

| Memory Bandwidth | 1.79 TB/s | System Dependent |

| Shading Units | 24064 | 1024 |

| TMUs | 752 | 64 |

| ROPs | 192 | 32 |

| RT Cores | 188 | 16 |

| Tensor Cores | 752 | None |

| Pixel Rate | 437.8 GPixel/s | 92.80 GPixel/s |

| Texture Rate | 1,714.6 GTexel/s | 185.6 GTexel/s |

| FP32 | 109.7 TFLOPS | 5.939 TFLOPS |

| FP16 | 109.7 TFLOPS (1:1) | 5.939 TFLOPS (1:1) |

| TDP | 300 W | 15 W |

| Slot Width | Dual-slot | IGP |

| Power Connectors | 1x 16-pin | None |

| Bus Interface | PCIe 5.0 x16 | PCIe 4.0 x8 |

| Display Outputs | 4x DisplayPort 2.1b | Portable Device Dependent |

| Release Date | 2025-03-17 | 2024-07-14 |

Head-to-Head Benchmarks

The only shared benchmark in the database is 3DMark Steel Nomad DX12. The NVIDIA RTX PRO 6000 Blackwell Max-Q scores 11088, while the AMD Radeon 890M scores 590. The delta is 1779.3%, making it a complete sweep in favor of the NVIDIA product. This is not a marginal lead; it is a performance gap of nearly 19 times. The NVIDIA card’s score places it at the 50th percentile versus all GPUs, while the AMD IGP sits at the 45th percentile, yet the absolute scores are far apart because the percentile ranking is relative to different pools of comparable devices.

For the AMD Radeon 890M, other benchmarks in the database show it is a capable integrated solution in its own right. Its Geekbench OpenCL score is 37254 and its Vulkan score is 40808, with a Passmark G3D score of 8076 and a Passmark GPU compute score of 4157. These numbers indicate that the AMD IGP is not a weak part for its class, but they cannot be compared to the NVIDIA card because the NVIDIA card lacks those specific test results. The only direct comparison, Steel Nomad, shows a decisive NVIDIA victory.

Where Each One Wins

The NVIDIA RTX PRO 6000 Blackwell Max-Q wins every direct comparison in the database. It dominates in 3DMark Steel Nomad DX12, the only head-to-head test recorded. Its architectural resources are overwhelming: 24,064 shading units, 752 TMUs, 192 ROPs, 188 RT cores, and 752 tensor cores. With 96 GB of GDDR7 and 1.79 TB/s of bandwidth, it is built for heavy professional rendering, large model loads, and compute-intensive workloads. Its 300 W TDP and dual-slot design indicate it is meant for a desktop workstation with a substantial power supply, and its 4x DisplayPort 2.1b outputs support multi-monitor professional setups.

The AMD Radeon 890M wins in efficiency and portability, though not in any benchmark comparison. Its 15 W TDP is 20 times lower than the NVIDIA card, and it requires no power connector, using the system’s shared memory for its frame buffer. It is an IGP, meaning it is integrated into a mobile or compact platform, with display outputs dependent on the portable device. Its higher boost clock of 2900 MHz and higher transistor density show a design optimized for low power, not peak performance. For light gaming, basic video playback, or general desktop acceleration in a thin-and-light laptop, the AMD part is the only viable choice here because the NVIDIA card cannot fit or be powered in such a system. But for any workload where the NVIDIA card can be installed, the data shows it wins decisively.