NVIDIA GeForce RTX 5090 D vs Lisuan Tech LX PRO Comparison

Head-to-Head Benchmarks

The recorded data shows a stark contrast between these two GPUs, though direct comparison is limited by the fact that the Lisuan Tech LX PRO has no recorded benchmark scores in the database. The NVIDIA GeForce RTX 5090 D carries an average benchmark score of 77712, placing it in the 92nd percentile of all GPUs tracked. The Lisuan Tech LX PRO holds a 50th percentile position with an average benchmark score of 0, indicating no measured results have been entered.

For the RTX 5090 D, the individual benchmark results reveal its strongest areas. In 3DMark Steel Nomad DX12, it scores 14326 points. Geekbench OpenCL returns 310674, while Geekbench Vulkan reaches 376915. Passmark tests show a G3D score of 44065, GPU Compute at 28396, and G2D at 1487. Legacy DirectX tests produce scores of 434 for DX9, 371 for DX11, 231 for DX10, and 219 for DX12. The average of all these tests is 77712.

The nearest rivals for the RTX 5090 D, based on average score, are the AMD Radeon RX 665M XT at 76904 (1.1% lower), the AMD Radeon RX 6850M XT at 78940 (1.6% higher), the NVIDIA Tesla P100 PCIe 12 GB at 79396 (2.1% higher), and the NVIDIA Tesla P100 PCIe 16 GB at 79605 (2.4% higher). These deltas indicate the RTX 5090 D sits in a narrow competitive band around these mobile and data center parts, despite its much larger specifications.

Since the LX PRO has no recorded benchmarks, the head-to-head comparison must rely entirely on specification-derived performance indicators. The RTX 5090 D delivers 104.8 TFLOPS FP32, while the LX PRO delivers 24.58 TFLOPS FP32. That represents a 4.3x advantage for the NVIDIA part in raw shader throughput. Pixel rate favors the RTX 5090 D at 423.6 GPixel/s versus 192.0 GPixel/s, a 2.2x difference. Texture rate shows 1,636.8 GTexel/s for the RTX 5090 D versus 384.0 GTexel/s for the LX PRO, a 4.3x gap. Memory bandwidth is 1.79 TB/s on the RTX 5090 D versus 432.0 GB/s on the LX PRO, a 4.1x difference.

The RTX 5090 D leads in every measurable specification category where both have data. The LX PRO does have a higher memory clock in terms of effective data rate per pin: 18 Gbps effective versus 28 Gbps effective on the RTX 5090 D, but the latter uses GDDR7 on a 512-bit bus, while the former uses GDDR6 on a 192-bit bus. The RTX 5090 D doubles the memory bus width and uses a newer memory type, explaining the bandwidth gap.

Architecture Differences

The RTX 5090 D uses the GB202 chip built on Blackwell 2.0 architecture, fabricated on a 5 nm process at TSMC. It contains 92,200 million transistors on a 750 mm² die, yielding a transistor density of 122.9M per mm². The LX PRO uses the 7G105 chip with TrueGPU architecture, fabricated on a 6 nm process at TSMC. Transistor count and die size are unknown for the LX PRO, and no density figure is recorded.

Shading units differ substantially: the RTX 5090 D has 21,760 shading units, 680 texture mapping units, and 176 ROPs. The LX PRO has 6,144 shading units, 192 TMUs, and 96 ROPs. The RTX 5090 D also integrates 170 RT cores and 680 tensor cores, while the LX PRO lists no RT core or tensor core counts in the database. This suggests ray tracing and tensor acceleration hardware is either absent or unspecified for the Lisuan part.

Memory configurations diverge sharply. The RTX 5090 D offers 32 GB of GDDR7 across a 512-bit bus, with bandwidth of 1.79 TB/s. The LX PRO offers 24 GB of GDDR6 across a 192-bit bus, with bandwidth of 432.0 GB/s. Memory clock data shows the RTX 5090 D at 1750 MHz (28 Gbps effective) and the LX PRO at 2250 MHz (18 Gbps effective). The newer GDDR7 standard and wider bus give the NVIDIA card a decisive memory advantage.

FP16 throughput also differentiates the architectures. The RTX 5090 D achieves 104.8 TFLOPS FP16 with a 1:1 ratio to FP32, meaning identical throughput for both precisions. The LX PRO achieves 49.15 TFLOPS FP16 with a 2:1 ratio to FP32, meaning FP16 is half the FP32 rate. The NVIDIA implementation likely uses dedicated tensor hardware for FP16, while the LX PRO appears to use a conventional shader-based approach.

API support shows the RTX 5090 D supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The LX PRO supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.3. Both meet the latest DirectX standard, but the NVIDIA card has a newer Vulkan version.

Power consumption reflects the performance differential. The RTX 5090 D has a TDP of 575 W with a suggested 950 W power supply, while the LX PRO has a TDP of 225 W with a suggested 550 W power supply. Both use a single 16-pin power connector and dual-slot cooling. The RTX 5090 D runs at 2017 MHz base and 2407 MHz boost clocks. The LX PRO has no base or boost clock data recorded.

Physical dimensions differ: the RTX 5090 D measures 304 mm in length, 137 mm in height, and 48 mm in width. The LX PRO measures 248 mm in length, 118 mm in height, and 48 mm in width. The NVIDIA card is longer and taller, consistent with its larger cooler requirement.

Display outputs differ as well. The RTX 5090 D provides 1x HDMI 2.1b and 3x DisplayPort 2.1b. The LX PRO provides 4x DisplayPort 1.4a. The NVIDIA card supports newer display standards, including higher bandwidth DisplayPort 2.1b versus the older DisplayPort 1.4a on the Lisuan part.

Release timing separates the two: the RTX 5090 D launched on 2025-01-29, while the LX PRO launched on 2026-03-16. The NVIDIA card has a predecessor in GeForce 40 and a successor in GeForce 60, while the LX PRO lists no predecessor or successor. The RTX 5090 D carries a launch MSRP of 2,299 USD, while the LX PRO has no recorded launch MSRP.

The Verdict

The data supports a clear conclusion: the NVIDIA GeForce RTX 5090 D is the superior performer by every recorded metric. Its FP32 throughput of 104.8 TFLOPS is 4.3x higher than the LX PRO's 24.58 TFLOPS. Memory bandwidth of 1.79 TB/s is 4.1x higher than 432.0 GB/s. Pixel rate is 2.2x higher, and texture rate is 4.3x higher. The RTX 5090 D also carries more shading units (21,760 versus 6,144), more TMUs (680 versus 192), more ROPs (176 versus 96), and more memory (32 GB versus 24 GB).

The LX PRO's advantages are limited to lower power draw (225 W versus 575 W), smaller physical footprint (248 mm versus 304 mm length), and a later release date. For workloads where power efficiency matters, the LX PRO uses 2.6x less power while delivering roughly one quarter of the FP32 throughput, suggesting similar efficiency per watt in raw compute. However, the LX PRO has no benchmark scores to validate real-world performance, while the RTX 5090 D has an extensive record.

The percentile rankings reinforce the gap: the RTX 5090 D sits in the 92nd percentile of all GPUs, while the LX PRO sits at the 50th percentile. The RTX 5090 D's nearest rivals are within a 2.4% band of its average score, indicating it is a competitive high-end part. The LX PRO has no recorded rivals, which limits context but also reflects its unmeasured status.

For users prioritizing absolute performance, the RTX 5090 D is the only choice with measured data. The LX PRO remains an unknown quantity in the database, with no benchmarks to substantiate its specifications.

Specification Differences

The following fields differ between the two GPUs:

• Process node: 5 nm (RTX 5090 D) versus 6 nm (LX PRO)
• Transistors: 92,200 million (RTX 5090 D) versus unknown (LX PRO)
• Die size: 750 mm² (RTX 5090 D) versus unknown (LX PRO)
• Transistor density: 122.9M / mm² (RTX 5090 D) versus not recorded (LX PRO)
• Base clock: 2017 MHz (RTX 5090 D) versus not recorded (LX PRO)
• Boost clock: 2407 MHz (RTX 5090 D) versus not recorded (LX PRO)
• Memory clock: 1750 MHz, 28 Gbps effective (RTX 5090 D) versus 2250 MHz, 18 Gbps effective (LX PRO)
• Memory size: 32 GB (RTX 5090 D) versus 24 GB (LX PRO)
• Memory type: GDDR7 (RTX 5090 D) versus GDDR6 (LX PRO)
• Memory bus width: 512 bit (RTX 5090 D) versus 192 bit (LX PRO)
• Memory bandwidth: 1.79 TB/s (RTX 5090 D) versus 432.0 GB/s (LX PRO)
• Shading units: 21,760 (RTX 5090 D) versus 6,144 (LX PRO)
• TMUs: 680 (RTX 5090 D) versus 192 (LX PRO)
• ROPs: 176 (RTX 5090 D) versus 96 (LX PRO)
• RT cores: 170 (RTX 5090 D) versus not recorded (LX PRO)
• Tensor cores: 680 (RTX 5090 D) versus not recorded (LX PRO)
• Pixel rate: 423.6 GPixel/s (RTX 5090 D) versus 192.0 GPixel/s (LX PRO)
• Texture rate: 1,636.8 GTexel/s (RTX 5090 D) versus 384.0 GTexel/s (LX PRO)
• FP32: 104.8 TFLOPS (RTX 5090 D) versus 24.58 TFLOPS (LX PRO)
• FP16: 104.8 TFLOPS, 1:1 ratio (RTX 5090 D) versus 49.15 TFLOPS, 2:1 ratio (LX PRO)
• TDP: 575 W (RTX 5090 D) versus 225 W (LX PRO)
• Suggested PSU: 950 W (RTX 5090 D) versus 550 W (LX PRO)
• Bus interface: PCIe 5.0 x16 (RTX 5090 D) versus PCIe 4.0 x16 (LX PRO)
• Display outputs: 1x HDMI 2.1b, 3x DisplayPort 2.1b (RTX 5090 D) versus 4x DisplayPort 1.4a (LX PRO)
• Vulkan version: 1.4 (RTX 5090 D) versus 1.3 (LX PRO)
• Dimensions: 304 mm x 137 mm x 48 mm (RTX 5090 D) versus 248 mm x 118 mm x 48 mm (LX PRO)
• Release date: 2025-01-29 (RTX 5090 D) versus 2026-03-16 (LX PRO)
• Predecessor: GeForce 40 (RTX 5090 D) versus not recorded (LX PRO)
• Successor: GeForce 60 (RTX 5090 D) versus not recorded (LX PRO)
• Launch MSRP: 2,299 USD (RTX 5090 D) versus not recorded (LX PRO)
• Percentile: 92 (RTX 5090 D) versus 50 (LX PRO)
• Average benchmark score: 77712 (RTX 5090 D) versus 0 (LX PRO)
• Nearest rivals: recorded for RTX 5090 D, none for LX PRO

Fields that match include: manufacturer foundry (TSMC for both), slot width (dual-slot for both), power connector (1x 16-pin for both), DirectX version (12 Ultimate 12_2 for both), OpenGL version (4.6 for both), card width (48 mm for both), and production status (Active for both).

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The RTX 5090 D delivers 104.8 TFLOPS FP32, which is 4.3x higher than the LX PRO's 24.58 TFLOPS.

Q: How do the memory configurations compare?

A: The RTX 5090 D uses 32 GB of GDDR7 on a 512-bit bus with 1.79 TB/s bandwidth. The LX PRO uses 24 GB of GDDR6 on a 192-bit bus with 432.0 GB/s bandwidth.

Q: Does the LX PRO support ray tracing?

A: The database does not record RT core or tensor core counts for the LX PRO. The RTX 5090 D has 170 RT cores and 680 tensor cores.

Q: Which GPU has lower power consumption?

A: The LX PRO has a TDP of 225 W with a suggested 550 W power supply, while the RTX 5090 D has a TDP of 575 W with a suggested 950 W power supply.

Q: What benchmark scores does the LX PRO have?

A: The database contains no benchmark scores for the LX PRO, giving it an average score of 0. The RTX 5090 D has scores across 3DMark, Geekbench, and Passmark tests.

Q: Which GPU has a newer display output standard?

A: The RTX 5090 D uses DisplayPort 2.1b and HDMI 2.1b. The LX PRO uses DisplayPort 1.4a only.

Where Each One Wins

The RTX 5090 D wins in every performance category with recorded data. Its FP32 throughput of 104.8 TFLOPS suits compute-heavy workloads such as scientific simulation, machine learning inference, and 3D rendering. The 1.79 TB/s memory bandwidth supports large dataset processing and high-resolution texture streaming. The 32 GB GDDR7 capacity accommodates massive scenes and models that exceed 24 GB. The 170 RT cores and 680 tensor cores provide dedicated hardware for ray tracing and AI acceleration, which the LX PRO lacks entirely.

The RTX 5090 D also wins on modern connectivity. PCIe 5.0 x16 doubles the bus bandwidth of the LX PRO's PCIe 4.0 x16 interface. DisplayPort 2.1b supports higher resolutions and refresh rates than DisplayPort 1.4a. Vulkan 1.4 support is newer than Vulkan 1.3 on the LX PRO.

The LX PRO wins on power efficiency and physical footprint. Its 225 W TDP is 350 W lower than the RTX 5090 D, requiring a 550 W power supply instead of 950 W. At 248 mm length, it fits in smaller cases compared to the RTX 5090 D's 304 mm length. These factors make the LX PRO suitable for compact builds or systems with limited power delivery.

The LX PRO also wins on release timing, launching on 2026-03-16 versus 2025-01-29 for the RTX 5090 D. However, without benchmark scores, the LX PRO's real-world performance cannot be verified. The RTX 5090 D has an extensive benchmark record placing it in the 92nd percentile, while the LX PRO sits at the 50th percentile with no measured results.

For users who need maximum performance, the RTX 5090 D is the only viable choice based on data. For users who prioritize low power consumption and small size, the LX PRO offers those advantages, but its performance remains unquantified in the database. The RTX 5090 D also has established nearest rivals within a 2.4% performance band, indicating its position among known high-performance parts. The LX PRO has no rival data, leaving its competitive standing undefined.