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

Head-to-Head Benchmarks

The data is unambiguous. The NVIDIA GeForce RTX 5090 Mobile defeats the AMD Radeon RX 6750 GRE 12 GB in every recorded head-to-head benchmark. In the 3DMark Steel Nomad DX12 test, the RTX 5090 Mobile scores 5871 against the RX 6750 GRE's 2402, a delta of -59.1% for AMD. That is a massive gap, placing NVIDIA's mobile part more than two and a half times ahead in this direct comparison.

The Vulkan results tell a similar story, though the margin narrows. The RTX 5090 Mobile posts 198405 in Geekbench Vulkan, while the RX 6750 GRE manages 108994. The delta here is -45.1%, meaning NVIDIA still leads by a wide margin, but the AMD card is relatively closer in this API than in DX12. This pattern suggests the RTX 5090 Mobile scales exceptionally well in modern DirectX 12 workloads, while the Vulkan gap, though still decisive, is slightly less punishing.

Looking at the broader benchmark database, the two cards occupy different performance tiers. The RTX 5090 Mobile holds a percentile rank of 84 among all GPUs, while the RX 6750 GRE sits at 87. This is counterintuitive given the head-to-head results, but the explanation lies in the benchmark suite composition. The RTX 5090 Mobile's average benchmark score of 45152 is dragged down by low PassMark DirectX 9, 10, 11, and 12 scores (324, 183, 269, and 138 respectively), which appear anomalous for a card of this capability. The RX 6750 GRE's average score of 55698 benefits from having only two recorded benchmarks, both of which are modern and demanding.

When comparing to their nearest rivals, both cards sit in competitive positions. The RX 6750 GRE is essentially tied with the AMD Radeon 8060S (delta -0.1%) and the NVIDIA GeForce RTX 5080 (delta -0.7%), while leading the AMD Radeon Pro W5700X by 1.6% and the RTX 4080 by 2.7%. The RTX 5090 Mobile trails the AMD Radeon Pro 5500 XT by 0.5%, leads the RTX 4070 Ti by 0.8%, and sits 1% below the Intel Arc A730M and 1.8% below the NVIDIA RTX 5880 Ada Generation. These narrow deltas around the RTX 5090 Mobile suggest its average score is heavily influenced by those anomalous PassMark entries, making its true competitive position unclear from the aggregated data alone.

Architecture Differences

The two GPUs come from fundamentally different design philosophies. AMD's RX 6750 GRE uses the Navi 22 chip built on RDNA 2.0 architecture, fabricated on TSMC's 7 nm process. NVIDIA's RTX 5090 Mobile uses the GB203 chip built on Blackwell 2.0, fabricated on TSMC's 5 nm process. The transistor counts reflect this generational leap: AMD packs 17,200 million transistors into a 335 mm² die, yielding a density of 51.3 million transistors per mm². NVIDIA crams 45,600 million transistors into a 378 mm² die, achieving a density of 120.6 million per mm². That is more than double the transistor density, which explains how NVIDIA fits far more compute resources into a similar physical footprint.

The memory subsystems are equally distinct. The RX 6750 GRE uses 12 GB of GDDR6 on a 192-bit bus, delivering 432.0 GB/s of bandwidth. The RTX 5090 Mobile uses 24 GB of GDDR7 on a 256-bit bus, delivering 896.0 GB/s. NVIDIA's memory bandwidth is more than double AMD's, and the capacity advantage is also 2x. This has direct implications for high-resolution textures and compute workloads that spill beyond 12 GB.

Compute resources favor NVIDIA overwhelmingly. The RTX 5090 Mobile has 10496 shading units, 328 TMUs, 112 ROPs, 82 RT cores, and 328 tensor cores. The RX 6750 GRE has 2560 shading units, 160 TMUs, 64 ROPs, and 40 RT cores, with no tensor cores listed. NVIDIA's FP32 throughput is 31.80 TFLOPS, compared to AMD's 13.21 TFLOPS. Interestingly, NVIDIA's FP16 throughput is identical to FP32 at 31.80 TFLOPS (1:1 ratio), whereas AMD's FP16 is 26.43 TFLOPS (2:1 ratio). This means AMD can process half-precision data at double its FP32 rate, but NVIDIA's full-rate FP16 is still higher in absolute terms.

Clock speeds tell a different story. AMD runs at a 2321 MHz base and 2581 MHz boost, with a game clock of 2439 MHz. NVIDIA runs much lower clocks at 990 MHz base and 1515 MHz boost. The lower clocks are typical for a mobile part constrained by thermals, but NVIDIA compensates with raw core count and architectural efficiency. Pixel rates are nearly identical: AMD at 165.2 GPixel/s and NVIDIA at 169.7 GPixel/s. Texture rates differ more, with NVIDIA at 496.9 GTexel/s versus AMD's 413.0 GTexel/s.

Power and physical design diverge sharply. The RX 6750 GRE is a dual-slot desktop card with a 250 W TDP, requiring a 600 W power supply and using 1x 6-pin plus 1x 8-pin power connectors. The RTX 5090 Mobile is an integrated graphics processor (IGP) with a 95 W TDP, no power connectors, and portable-device-dependent display outputs. NVIDIA achieves dramatically higher performance at less than half the power draw, though the comparison is between a desktop card and a laptop part.

Where Each One Wins

The RTX 5090 Mobile wins everywhere the data records a direct comparison. In 3DMark Steel Nomad DX12, it leads by 59.1%. In Geekbench Vulkan, it leads by 45.1%. These are not situational wins; they are comprehensive victories across both tested APIs. For any workload relying on DX12 or Vulkan, the RTX 5090 Mobile is the clear choice based on the recorded benchmarks.

The RX 6750 GRE's advantages are structural rather than performance-based. It has a higher percentile rank at 87 versus 84, driven by its consistent performance in modern benchmarks and the absence of those low PassMark scores that drag down NVIDIA's average. The RX 6750 GRE also has a higher average benchmark score of 55698 versus 45152, though this metric is skewed by the different benchmark sets each card was tested on.

For use cases, the RTX 5090 Mobile excels in scenarios where memory capacity and bandwidth matter. Its 24 GB of GDDR7 and 896.0 GB/s bandwidth make it suited for large datasets, high-resolution textures, and compute workloads that exceed 12 GB. The 82 RT cores and 328 tensor cores position it for ray tracing and AI-accelerated tasks, though no specific ray tracing benchmarks are in the recorded data.

The RX 6750 GRE, being a desktop card with a 250 W TDP, is suited for systems where power constraints are less critical. Its 12 GB of GDDR6 is adequate for current games at conventional resolutions, and its 40 RT cores provide entry-level ray tracing capability. The card's 7 nm process and lower transistor count mean it draws more power relative to its performance, but in a desktop with a 600 W power supply, that is manageable.

Specification Differences

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

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

| Architecture | RDNA 2.0 | Blackwell 2.0 |

| Process node | 7 nm | 5 nm |

| Transistors | 17,200 million | 45,600 million |

| Die size | 335 mm² | 378 mm² |

| Transistor density | 51.3M / mm² | 120.6M / mm² |

| Base clock | 2321 MHz | 990 MHz |

| Boost clock | 2581 MHz | 1515 MHz |

| Memory size | 12 GB | 24 GB |

| Memory type | GDDR6 | GDDR7 |

| Memory bus | 192 bit | 256 bit |

| Memory bandwidth | 432.0 GB/s | 896.0 GB/s |

| Shading units | 2560 | 10496 |

| TMUs | 160 | 328 |

| ROPs | 64 | 112 |

| RT cores | 40 | 82 |

| Tensor cores | None | 328 |

| Pixel rate | 165.2 GPixel/s | 169.7 GPixel/s |

| Texture rate | 413.0 GTexel/s | 496.9 GTexel/s |

| FP32 | 13.21 TFLOPS | 31.80 TFLOPS |

| FP16 | 26.43 TFLOPS (2:1) | 31.80 TFLOPS (1:1) |

| TDP | 250 W | 95 W |

| Slot width | Dual-slot | IGP |

| Power connectors | 1x 6-pin + 1x 8-pin | None |

| Bus interface | PCIe 4.0 x16 | PCIe 5.0 x16 |

| Game clock | 2439 MHz | Not listed |

| Memory clock | 2250 MHz, 18 Gbps effective | 1750 MHz, 28 Gbps effective |

| Suggested PSU | 600 W | Not listed |

| Dimensions | 267 mm x 110 mm x 40 mm | Not listed |

| Launch MSRP | 334 USD | Not listed |

| Release date | 2023-10-16 | 2025-03-26 |

FAQ

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

A: The NVIDIA GeForce RTX 5090 Mobile wins decisively with a score of 5871 versus the AMD Radeon RX 6750 GRE's 2402, a delta of -59.1% for AMD.

Q: How do the two compare in Geekbench Vulkan?

A: The RTX 5090 Mobile scores 198405 against the RX 6750 GRE's 108994, a delta of -45.1%. NVIDIA leads, but AMD is relatively closer in Vulkan than in DX12.

Q: What are the memory differences?

A: The RX 6750 GRE has 12 GB of GDDR6 on a 192-bit bus with 432.0 GB/s bandwidth. The RTX 5090 Mobile has 24 GB of GDDR7 on a 256-bit bus with 896.0 GB/s bandwidth.

Q: Which GPU has higher percentile ranking?

A: The RX 6750 GRE ranks at the 87th percentile among all GPUs, while the RTX 5090 Mobile ranks at the 84th percentile. This is despite NVIDIA's direct benchmark wins.

Q: What is the power draw difference?

A: The RX 6750 GRE has a 250 W TDP and requires a 600 W power supply. The RTX 5090 Mobile has a 95 W TDP and requires no external power connectors.

Q: How do the FP32 throughput numbers compare?

A: The RTX 5090 Mobile delivers 31.80 TFLOPS of FP32 performance, while the RX 6750 GRE delivers 13.21 TFLOPS. NVIDIA has more than double the single-precision compute throughput.

The Verdict

The data points to one conclusion: the NVIDIA GeForce RTX 5090 Mobile is the superior performer in every recorded benchmark. Its 59.1% lead in 3DMark Steel Nomad and 45.1% lead in Geekbench Vulkan are substantial and consistent. The RTX 5090 Mobile also offers double the memory capacity, more than double the bandwidth, and more than double the FP32 compute throughput. Its 82 RT cores and 328 tensor cores provide capabilities that the RX 6750 GRE cannot match, as the AMD card has no tensor cores and fewer RT cores.

The RX 6750 GRE does have a higher percentile rank of 87 versus 84, but this is an artifact of the benchmark sets used. The AMD card's two recorded benchmarks are both modern and demanding, while the RTX 5090 Mobile's average is pulled down by low PassMark scores in legacy DirectX tests. These PassMark numbers appear inconsistent with the card's performance in modern workloads and should be treated with skepticism.

For users building a desktop system with a 600 W power supply and seeking a solid 12 GB card, the RX 6750 GRE is a functional choice, and its launch MSRP of 334 USD reflects its positioning. However, for anyone comparing these two specific GPUs, the RTX 5090 Mobile wins on raw performance, memory capacity, bandwidth, and efficiency. The only advantages the RX 6750 GRE holds are its higher percentile rank and higher average benchmark score, both of which are explained by benchmark composition rather than actual performance superiority.

The RTX 5090 Mobile is the pick for maximum performance, especially in DX12 and Vulkan workloads, and for tasks that benefit from 24 GB of GDDR7 memory. The RX 6750 GRE makes sense only if the desktop form factor, 12 GB capacity, and specific power supply requirements align with a build that does not need the NVIDIA card's compute and ray tracing capabilities. Based strictly on the recorded data, there is no benchmark scenario where the RX 6750 GRE comes out ahead.