AMD Radeon RX 6750 GRE 12 GB vs NVIDIA GeForce RTX 5090 Comparison

Head-to-Head Benchmarks

The benchmark database records two direct comparison points between the NVIDIA GeForce RTX 5090 and the AMD Radeon RX 6750 GRE 12 GB. In both tests, the RTX 5090 dominates decisively.

In the 3DMark Steel Nomad DX12 test, the RTX 5090 scores 18,355 points against 2,402 points for the RX 6750 GRE. That is a 664.2% advantage, the largest delta in the recorded head-to-head set. The gap is so wide that the RX 6750 GRE's score is only about 13% of the RTX 5090's result in this workload.

The Geekbench Vulkan test shows a similar pattern, though slightly less extreme. The RTX 5090 records 376,728 points, while the RX 6750 GRE manages 108,994 points. The delta here is 245.6%. Both tests are compute-heavy, but the Vulkan result narrows the gap somewhat, suggesting the AMD architecture is comparatively stronger in that API than in DirectX 12.

The RTX 5090 wins both recorded head-to-head benchmarks. The wins tally is 2 for the NVIDIA card and 0 for the AMD card. No test in the database flips in favor of the RX 6750 GRE.

Looking at the broader average benchmark scores, the RTX 5090 sits at 79,842 points, while the RX 6750 GRE averages 55,698 points. That difference works out to roughly 43% higher average performance for the RTX 5090 across all recorded tests. The percentile rankings reinforce this: the RTX 5090 falls in the 92nd percentile of all GPUs, whereas the RX 6750 GRE sits in the 87th percentile.

The nearest rivals data places each card in its own competitive neighborhood. The RTX 5090's closest competitors include the NVIDIA Tesla P100 PCIe 16 GB at 79,605 points (0.3% behind), the Tesla P100 PCIe 12 GB at 79,396 points (0.6% behind), and the AMD Radeon RX 6850M XT at 78,940 points (1.1% behind). The AMD Radeon Pro Vega 64X sits 1.4% ahead at 80,959 points. These are all within a few percentage points, meaning the RTX 5090's average score is tightly clustered among high-end workstation and mobile parts.

The RX 6750 GRE's nearest rivals tell a different story. The AMD Radeon 8060S is essentially tied at 55,757 points (0.1% behind the RX 6750 GRE). The NVIDIA GeForce RTX 5080 trails by 0.7% at 56,083 points. The AMD Radeon Pro W5700X is 1.6% behind at 54,828 points, and the NVIDIA GeForce RTX 4080 is 2.7% behind at 54,247 points. This places the RX 6750 GRE in a much lower performance tier, competing with mid-range and previous-generation parts rather than flagship GPUs.

Architecture Differences

The two cards come from fundamentally different design generations. The RTX 5090 uses the GB202 chip built on the Blackwell 2.0 architecture, fabricated on a 5 nm process at TSMC. The RX 6750 GRE uses the Navi 22 chip with RDNA 2.0 architecture, also on a TSMC process but the older 7 nm node.

The transistor counts are wildly different. The RTX 5090 packs 92,200 million transistors on a 750 mm² die, resulting in a transistor density of 122.9 million per square millimeter. The RX 6750 GRE has 17,200 million transistors on a 335 mm² die, for a density of 51.3 million per square millimeter. The RTX 5090 has more than five times the transistor budget and more than double the die area.

Memory configurations diverge sharply as well. The RTX 5090 ships with 32 GB of GDDR7 memory on a 512-bit bus, delivering 1.79 TB/s of bandwidth. The RX 6750 GRE offers 12 GB of GDDR6 on a 192-bit bus, with 432.0 GB/s of bandwidth. That is roughly a 4x difference in memory capacity and a 4.1x difference in bandwidth.

The compute resources are similarly lopsided. The RTX 5090 has 21,760 shading units, 680 TMUs, and 176 ROPs. It also includes 170 ray tracing cores and 680 tensor cores. The RX 6750 GRE has 2,560 shading units, 160 TMUs, and 64 ROPs, with 40 ray tracing cores and no tensor cores at all. The shading unit count alone is 8.5x higher on the NVIDIA card.

Clock speeds complicate the comparison. The RX 6750 GRE actually runs higher clocks: 2,321 MHz base, 2,581 MHz boost, and a 2,439 MHz game clock. The RTX 5090 runs at 2,017 MHz base and 2,407 MHz boost. The AMD card's higher clocks cannot compensate for the massive difference in execution resources.

The RTX 5090 supports FP32 at 104.8 TFLOPS and FP16 at 104.8 TFLOPS in a 1:1 ratio. The RX 6750 GRE delivers 13.21 TFLOPS FP32 and 26.43 TFLOPS FP16 at a 2:1 ratio. The FP32 throughput gap is roughly 7.9x in favor of the RTX 5090.

Power requirements differ substantially. The RTX 5090 has a TDP of 575 W and requires a 950 W suggested PSU, with a single 16-pin power connector. The RX 6750 GRE has a 250 W TDP, a 600 W suggested PSU, and uses a 6-pin plus 8-pin connector arrangement.

Interface support also differs. The RTX 5090 uses PCIe 5.0 x16, while the RX 6750 GRE uses PCIe 4.0 x16. Display outputs are similar in count but different in version: the RTX 5090 offers 1x HDMI 2.1b and 3x DisplayPort 2.1b, while the RX 6750 GRE offers 1x HDMI 2.1 and 3x DisplayPort 1.4a.

The Verdict

The data is unambiguous. The RTX 5090 outperforms the RX 6750 GRE by enormous margins in every recorded benchmark. In 3DMark Steel Nomad DX12, the RTX 5090 leads by 664.2%. In Geekbench Vulkan, it leads by 245.6%. The average benchmark score gap is about 43% in favor of the RTX 5090.

The RTX 5090 is the clear choice for anyone prioritizing raw performance, ray tracing capability, and memory bandwidth. Its 32 GB of GDDR7 memory and 1.79 TB/s bandwidth place it in a completely different class from the RX 6750 GRE's 12 GB GDDR6 and 432.0 GB/s. The tensor cores, present only on the NVIDIA card, also make it the only option here for AI workloads or applications that leverage tensor acceleration.

The RX 6750 GRE, however, does have its own profile. Its higher base and boost clocks suggest it can be efficient in certain lightly threaded or clock-sensitive workloads. Its nearest rivals, including the RTX 5080 and RTX 4080, are within 2.7% of its average score, indicating it sits comfortably in the mid-range tier. The 87th percentile ranking means it still outperforms the majority of GPUs in the database.

For a user whose workload demands maximum frame rates, high-resolution rendering, or compute-heavy tasks, the RTX 5090 is the only rational pick based on the recorded data. For a user with lighter requirements, the RX 6750 GRE delivers respectable performance at a much lower power envelope, 250 W versus 575 W, and a smaller physical footprint, 267 mm versus 304 mm in length. The choice depends entirely on whether the performance gap justifies the massive difference in power draw and system requirements.

Specification Differences

| Specification | NVIDIA GeForce RTX 5090 | AMD Radeon RX 6750 GRE 12 GB |

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

| Chip | GB202 | Navi 22 |

| Architecture | Blackwell 2.0 | RDNA 2.0 |

| Process Node | 5 nm | 7 nm |

| Transistors | 92,200 million | 17,200 million |

| Die Size | 750 mm² | 335 mm² |

| Transistor Density | 122.9M / mm² | 51.3M / mm² |

| Base Clock | 2017 MHz | 2321 MHz |

| Boost Clock | 2407 MHz | 2581 MHz |

| Game Clock | Not specified | 2439 MHz |

| Memory Size | 32 GB | 12 GB |

| Memory Type | GDDR7 | GDDR6 |

| Memory Bus Width | 512 bit | 192 bit |

| Memory Bandwidth | 1.79 TB/s | 432.0 GB/s |

| Shading Units | 21760 | 2560 |

| TMUs | 680 | 160 |

| ROPs | 176 | 64 |

| Ray Tracing Cores | 170 | 40 |

| Tensor Cores | 680 | Not present |

| Pixel Rate | 423.6 GPixel/s | 165.2 GPixel/s |

| Texture Rate | 1,636.8 GTexel/s | 413.0 GTexel/s |

| FP32 Performance | 104.8 TFLOPS | 13.21 TFLOPS |

| FP16 Performance | 104.8 TFLOPS (1:1) | 26.43 TFLOPS (2:1) |

| TDP | 575 W | 250 W |

| Power Connectors | 1x 16-pin | 1x 6-pin + 1x 8-pin |

| Suggested PSU | 950 W | 600 W |

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

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

| Length | 304 mm | 267 mm |

| Height | 137 mm | 110 mm |

| Width | 40 mm | 40 mm |

| Release Date | 2025-01-29 | 2023-10-16 |

| Launch MSRP | 1,999 USD | 334 USD |

FAQ

Q: Which card wins in 3DMark Steel Nomad DX12?

A: The NVIDIA GeForce RTX 5090 scores 18,355 points versus 2,402 for the AMD Radeon RX 6750 GRE, a 664.2% advantage.

Q: How much faster is the RTX 5090 in Geekbench Vulkan?

A: The RTX 5090 scores 376,728 points against 108,994 for the RX 6750 GRE, which is 245.6% higher.

Q: What is the average benchmark score difference between the two cards?

A: The RTX 5090 averages 79,842 points, while the RX 6750 GRE averages 55,698 points, a difference of roughly 43% in favor of the NVIDIA card.

Q: How do the memory configurations compare?

A: The RTX 5090 has 32 GB of GDDR7 on a 512-bit bus with 1.79 TB/s bandwidth. The RX 6750 GRE has 12 GB of GDDR6 on a 192-bit bus with 432.0 GB/s bandwidth.

Q: Does the RX 6750 GRE have tensor cores?

A: No. The RTX 5090 has 680 tensor cores, while the RX 6750 GRE does not list any tensor cores in the database.

Q: How do the power requirements differ?

A: The RTX 5090 has a TDP of 575 W and a suggested PSU of 950 W. The RX 6750 GRE has a TDP of 250 W and a suggested PSU of 600 W.

Q: What are the nearest rivals for each card based on average score?

A: The RTX 5090's closest rival is the NVIDIA Tesla P100 PCIe 16 GB at 79,605 points (0.3% behind). The RX 6750 GRE's closest rival is the AMD Radeon 8060S at 55,757 points (0.1% behind).