NVIDIA GeForce RTX 5090 D vs Lisuan Tech LX 7G100 Comparison

FAQ

Q: What is the process node difference between the two cards?

A: The NVIDIA GeForce RTX 5090 D uses a 5 nm process at TSMC, while the Lisuan Tech LX 7G100 uses a 6 nm process at the same foundry.

Q: How much memory does each card have and what type?

A: The RTX 5090 D has 32 GB of GDDR7 memory on a 512-bit bus, while the LX 7G100 has 12 GB of GDDR6 memory on a 192-bit bus.

Q: Which card has a higher memory bandwidth?

A: The RTX 5090 D delivers 1.79 TB/s bandwidth, which is substantially higher than the LX 7G100's 432.0 GB/s.

Q: What are the shading unit counts?

A: The RTX 5090 D has 21,760 shading units, while the LX 7G100 has 6,144 shading units.

Q: Does the LX 7G100 have ray tracing or tensor cores?

A: No, the database lists no RT core count and no tensor core count for the LX 7G100. The RTX 5090 D has 170 RT cores and 680 tensor cores.

Q: What is the release date for each card?

A: The RTX 5090 D was released on 2025-01-29, while the LX 7G100 has a release date of 2026-06-17.

Architecture Differences

The NVIDIA GeForce RTX 5090 D uses the GB202 chip built on the Blackwell 2.0 architecture, while the Lisuan Tech LX 7G100 uses the 7G106 chip built on the TrueGPU architecture. This architectural split produces major differences in compute structure.

The RTX 5090 D packs 92,200 million transistors on a 750 mm² die, giving a transistor density of 122.9M per mm². The LX 7G100 has no recorded transistor count, die size, or density figures in the database. However, the process node differs: 5 nm for the RTX 5090 D versus 6 nm for the LX 7G100, both at TSMC.

The shading unit count shows the scale of the gap. The RTX 5090 D carries 21,760 shading units, 680 TMUs, and 176 ROPs. The LX 7G100 has 6,144 shading units, 192 TMUs, and 96 ROPs. That is roughly 3.5 times the shading units and 3.5 times the TMUs on the NVIDIA side, and nearly double the ROPs.

Ray tracing and tensor hardware exist only on the RTX 5090 D in this comparison. The database records 170 RT cores and 680 tensor cores for the NVIDIA card. The LX 7G100 has no RT core or tensor core entries, meaning it lacks dedicated hardware for those workloads.

Clock behavior differs as well. The RTX 5090 D has a base clock of 2017 MHz and a boost clock of 2407 MHz. The LX 7G100 has no base or boost clock recorded. Memory clocks show 1750 MHz (28 Gbps effective) on the RTX 5090 D versus 2250 MHz (18 Gbps effective) on the LX 7G100. The higher effective data rate on the NVIDIA card is achieved through GDDR7, whereas the LX 7G100 uses GDDR6.

The FP32 compute output is 104.8 TFLOPS on the RTX 5090 D, while the LX 7G100 delivers 24.58 TFLOPS. That is a 4.3x difference. For FP16, the RTX 5090 D delivers 104.8 TFLOPS at a 1:1 ratio, while the LX 7G100 delivers 49.15 TFLOPS at a 2:1 ratio. The 1:1 ratio on the NVIDIA card means it does not split FP16 work across two cycles, so its FP16 throughput matches its FP32 throughput.

Pixel fill rate stands at 423.6 GPixel/s for the RTX 5090 D versus 192.0 GPixel/s for the LX 7G100. Texture fill rate is 1,636.8 GTexel/s versus 384.0 GTexel/s. Both figures indicate the NVIDIA card processes roughly 2.2 to 4.3 times the rasterization work per second.

The power delivery infrastructure also separates the two. The RTX 5090 D has a 575 W TDP with a single 16-pin connector and a suggested 950 W PSU. The LX 7G100 has a 225 W TDP with a single 8-pin connector and a suggested 550 W PSU. Both cards are dual-slot designs. The RTX 5090 D is 304 mm long, 137 mm tall, and 48 mm wide. The LX 7G100 is 294 mm long, 120 mm tall, and 49 mm wide.

Bus interfaces differ: PCIe 5.0 x16 on the RTX 5090 D versus PCIe 4.0 x16 on the LX 7G100. Display outputs show 1x HDMI 2.1b and 3x DisplayPort 2.1b on the NVIDIA card, while the LX 7G100 has 4x DisplayPort 1.4a. Both support DirectX 12 Ultimate (12_2) and OpenGL 4.6. The RTX 5090 D supports Vulkan 1.4; the LX 7G100 supports Vulkan 1.3.

The Verdict

The recorded data points to a single conclusion: the RTX 5090 D is the dominant performer in nearly every measured dimension. The LX 7G100 offers a lower-power alternative with much smaller compute resources, but it lacks benchmark scores entirely.

For users who need maximum rasterization, ray tracing, and tensor performance, the RTX 5090 D is the clear choice. It has more shading units, more TMUs, more ROPs, dedicated RT and tensor cores, larger memory, faster memory, and higher fill rates. Its 104.8 TFLOPS FP32 output and 1.79 TB/s bandwidth place it in a performance tier that the LX 7G100 cannot approach.

For users who prioritize lower power draw and a smaller physical footprint, the LX 7G100 draws 225 W versus 575 W, and its suggested PSU is 550 W versus 950 W. It is also slightly shorter (294 mm versus 304 mm) and shorter in height (120 mm versus 137 mm). The LX 7G100 still supports DirectX 12 Ultimate and OpenGL 4.6, so it can run modern game APIs, but its 24.58 TFLOPS FP32 output and 432.0 GB/s bandwidth set a much lower ceiling.

The database has no benchmark entries for the LX 7G100, so its actual performance in 3DMark Steel Nomad, Geekbench, or PassMark cannot be quantified. The RTX 5090 D has a full set of recorded scores across those tests. Without data, any performance claim for the LX 7G100 remains speculative.

The RTX 5090 D also carries a launch MSRP of 2,299 USD. The LX 7G100 has no recorded MSRP. The RTX 5090 D sits in the 92nd percentile of all GPUs in the database, while the LX 7G100 sits in the 50th percentile with an average benchmark score of 0.

Specification Differences

| Specification | RTX 5090 D | LX 7G100 |

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

| Process node | 5 nm | 6 nm |

| Transistors | 92,200 million | unknown |

| Die size | 750 mm² | unknown |

| Base clock | 2017 MHz | none recorded |

| Boost clock | 2407 MHz | none recorded |

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

| Memory size | 32 GB | 12 GB |

| Memory type | GDDR7 | GDDR6 |

| Bus width | 512 bit | 192 bit |

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

| Shading units | 21,760 | 6,144 |

| TMUs | 680 | 192 |

| ROPs | 176 | 96 |

| RT cores | 170 | none recorded |

| Tensor cores | 680 | none recorded |

| Pixel rate | 423.6 GPixel/s | 192.0 GPixel/s |

| Texture rate | 1,636.8 GTexel/s | 384.0 GTexel/s |

| FP32 | 104.8 TFLOPS | 24.58 TFLOPS |

| FP16 | 104.8 TFLOPS (1:1) | 49.15 TFLOPS (2:1) |

| TDP | 575 W | 225 W |

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

| Suggested PSU | 950 W | 550 W |

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

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

| Vulkan | 1.4 | 1.3 |

| Length | 304 mm | 294 mm |

| Height | 137 mm | 120 mm |

| Width | 48 mm | 49 mm |

| Release date | 2025-01-29 | 2026-06-17 |

| Percentile | 92 | 50 |

| Average benchmark score | 77,712 | 0 |

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark entries between the RTX 5090 D and the LX 7G100. The LX 7G100 has zero benchmark scores recorded, so no 3DMark, Geekbench, or PassMark results exist for it. The RTX 5090 D has ten recorded test scores.

In 3DMark Steel Nomad DX12, the RTX 5090 D scores 14,326. In Geekbench OpenCL, it scores 310,674. In Geekbench Vulkan, it scores 376,915. PassMark results show 231 for DirectX 10, 371 for DirectX 11, 219 for DirectX 12, 434 for DirectX 9, 1,487 for G2D, 44,065 for G3D, and 28,396 for GPU compute. The average benchmark score is 77,712.

Because the LX 7G100 has no recorded scores, the comparison cannot produce a per-test delta. Instead, the nearest rivals of the RTX 5090 D provide context. The AMD Radeon RX 6650M XT has an average score of 76,904, which is 1.1% below the RTX 5090 D. The AMD Radeon RX 6850M XT scores 78,940, which is 1.6% higher. The NVIDIA Tesla P100 PCIe 12 GB scores 79,396, which is 2.1% higher. The NVIDIA Tesla P100 PCIe 16 GB scores 79,605, which is 2.4% higher. This places the RTX 5090 D within a tight band around 77,000 to 79,000 average score, slightly below the top of that group.

The RTX 5090 D sits in the 92nd percentile of all GPUs, meaning it outperforms 92% of the database. The LX 7G100 sits in the 50th percentile with an average score of 0, which is the median position by definition but carries no actual performance data.

Where Each One Wins

The RTX 5090 D wins in every performance category where the database has recorded data. Its FP32 output of 104.8 TFLOPS is 4.3x the LX 7G100's 24.58 TFLOPS. Its texture rate of 1,636.8 GTexel/s is 4.3x the 384.0 GTexel/s of the LX 7G100. Its pixel rate of 423.6 GPixel/s is 2.2x the 192.0 GPixel/s of the LX 7G100.

Memory bandwidth heavily favors the RTX 5090 D. At 1.79 TB/s, it offers roughly 4.1x the 432.0 GB/s of the LX 7G100. The 32 GB GDDR7 memory also provides more than double the capacity of the 12 GB GDDR6 on the LX 7G100.

The RTX 5090 D also wins on API support. It supports Vulkan 1.4 versus Vulkan 1.3 on the LX 7G100. Both cards support DirectX 12 Ultimate and OpenGL 4.6. The RTX 5090 D has DisplayPort 2.1b outputs, while the LX 7G100 has DisplayPort 1.4a outputs. The RTX 5090 D uses PCIe 5.0 x16, while the LX 7G100 uses PCIe 4.0 x16.

The LX 7G100 wins in power efficiency and physical footprint. Its 225 W TDP is 350 W lower than the RTX 5090 D's 575 W. Its suggested PSU of 550 W is 400 W lower than the 950 W suggested for the RTX 5090 D. The LX 7G100 uses a single 8-pin connector, which is more compatible with older power supplies than the 16-pin connector on the RTX 5090 D. The LX 7G100 is also 10 mm shorter and 17 mm shorter in height, though it is 1 mm wider.

For compute workloads that rely on FP16, the LX 7G100's 49.15 TFLOPS at a 2:1 ratio is less than half of the RTX 5090 D's 104.8 TFLOPS at 1:1. The 1:1 ratio on the NVIDIA card means it does not halve throughput for FP16 operations, so its FP16 performance is identical to its FP32 performance. The LX 7G100 doubles its FP32 rate for FP16, but that still leaves it below the NVIDIA card.

For ray tracing and tensor workloads, only the RTX 5090 D has dedicated hardware. The LX 7G100 has no RT cores and no tensor cores recorded, so it must rely on general-purpose shader execution for those tasks, if it supports them at all.

For users who need maximum frame rates in DirectX 12 games, the RTX 5090 D's 21,760 shading units and 176 ROPs provide the raw throughput. For users who need lower system power draw and smaller card dimensions, the LX 7G100 offers a lighter configuration, but its lack of benchmark data means no performance verification exists.

The production status for both cards is Active. The RTX 5090 D has a predecessor in the GeForce 40 series and a successor in the GeForce 60 series, while the LX 7G100 has neither. The RTX 5090 D belongs to the GeForce 50-series generation, while the LX 7G100 belongs to the 7G100 generation.