AMD Radeon 890M vs Lisuan Tech LX PRO Comparison

The AMD Radeon 890M is an integrated graphics processor built on the Strix Point chip, using the RDNA 3.5 architecture and manufactured on a 4 nm process at TSMC. The Lisuan Tech LX PRO is a discrete graphics card featuring the 7G105 chip, using the TrueGPU architecture and manufactured on a 6 nm process, also at TSMC. The two devices occupy entirely different segments: the 890M is an IGP with a 15 W power envelope, while the LX PRO is a dual-slot card with a 225 W power envelope, 24 GB of GDDR6 memory, and a 192-bit memory bus. Benchmark data for the LX PRO is not yet recorded in the database, so the analysis below relies on architectural specifications and the measured results available for the 890M.

Where Each One Wins

The recorded benchmark suite contains ten scores for the AMD Radeon 890M, covering DirectX 9, 10, 11, and 12 workloads, OpenCL, Vulkan, and compute tests. The 890M’s highest relative performance appears in legacy DirectX 9 workloads, where it scores 97 in the PassMark DirectX 9 test, compared to 73 in DirectX 11, 37 in DirectX 12, and 33 in DirectX 10. This pattern indicates that the integrated part handles older API workloads with proportionally better efficiency, likely due to the RDNA 3.5 architecture’s compatibility with legacy shading paths. The 890M also delivers a PassMark G3D score of 8076 and a PassMark G2D score of 979, along with a GPU compute score of 4157.

The Lisuan Tech LX PRO has no benchmark entries in the database, so direct wins cannot be assigned from measured scores. However, the hardware specifications define clear domains where the LX PRO should dominate. The LX PRO provides 24.58 TFLOPS of FP32 compute, which is more than four times the 890M’s 5.939 TFLOPS. It also has 6144 shading units versus 1024, 192 texture mapping units versus 64, and 96 render output units versus 32. The LX PRO’s pixel rate is 192.0 GPixel/s and its texture rate is 384.0 GTexel/s, both roughly double the 890M’s 92.80 GPixel/s and 185.6 GTexel/s. For memory-bound workloads, the LX PRO’s 432.0 GB/s bandwidth far exceeds the system-shared memory configuration of the 890M, whose bandwidth is listed as system dependent.

The 890M wins in power efficiency and form factor. It consumes 15 W and requires no power connectors, while the LX PRO consumes 225 W and needs a 1x 16-pin connector with a suggested 550 W power supply. The 890M is an IGP with no slot width, fitting into any system with a compatible socket, whereas the LX PRO is a dual-slot card measuring 248 mm in length, 118 mm in height, and 48 mm in width. For portable devices, the 890M’s display outputs are portable device dependent, while the LX PRO offers 4x DisplayPort 1.4a outputs, which suits fixed desktop configurations.

Architecture Differences

The AMD Radeon 890M uses the RDNA 3.5 architecture, which is a continuation of the Navi III IGP lineage for Strix Point mobile processors. It is built on a 4 nm process at TSMC, with 34,000 million transistors on a 233 mm² die, yielding a transistor density of 145.9 million transistors per square millimeter. The chip runs at a base clock of 400 MHz and a boost clock of 2900 MHz. The memory subsystem is entirely system shared, meaning the size, type, bus width, and bandwidth all depend on the host system’s RAM configuration. The 890M supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, and it includes 16 ray tracing cores, though tensor cores are not specified. The FP16 performance is identical to FP32 at 5.939 TFLOPS, indicating a 1:1 ratio.

The Lisuan Tech LX PRO uses the TrueGPU architecture, which is a different design from RDNA. It is fabricated on a 6 nm process at TSMC, and the transistor count and die size are not recorded in the database. The LX PRO has no base or boost clock data, but its memory runs at 2250 MHz with 18 Gbps effective speed. The memory configuration is 24 GB of GDDR6 on a 192-bit bus, delivering 432.0 GB/s of bandwidth. The shading unit count is 6144, with 192 TMUs and 96 ROPs. The LX PRO does not list ray tracing cores or tensor cores. Its FP32 throughput is 24.58 TFLOPS, and FP16 is 49.15 TFLOPS with a 2:1 ratio, which differs from the 890M’s 1:1 ratio. The LX PRO supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.3, which is one version behind the 890M’s Vulkan 1.4.

The interface also differs: the 890M uses PCIe 4.0 x8, while the LX PRO uses PCIe 4.0 x16. The LX PRO’s larger bus width and dedicated memory give it a distinct architectural advantage for large datasets, whereas the 890M relies on shared system memory, which introduces latency and bandwidth variability. The LX PRO’s power delivery includes a 1x 16-pin connector, and its suggested power supply is 550 W. The 890M has no power connectors and a 15 W TDP. The LX PRO’s release date is recorded as 2026-03-17, while the 890M’s release date is 2024-07-15. The 890M’s predecessor is the Navi II IGP, and the LX PRO has no recorded predecessor.

The Verdict

From the recorded data, the AMD Radeon 890M is the only device with benchmark scores. Its average benchmark score is 9210, and its percentile rank among all GPUs is 45. The nearest rivals in the database are the AMD Radeon Vega 8 with an average score of 9221 and a delta of -0.1%, the NVIDIA GeForce GTX 960 at 9273 with -0.7%, the NVIDIA GeForce GTX 465 at 9294 with -0.9%, and the NVIDIA GeForce GTX 850M at 9302 with -1.0%. These deltas are all negative, meaning the 890M scores slightly lower than each of these rivals, but the differences are within 1%. This places the 890M in a narrow performance band around 9210 to 9302 points, effectively matching older discrete GPUs from the GTX 900 and GTX 400 series.

The Lisuan Tech LX PRO has an average benchmark score of 0 and a percentile rank of 50, with no nearest rivals listed. The percentile of 50 is a placeholder that does not reflect measured performance, as the score of 0 indicates no completed runs in the database. Therefore, any verdict must separate measured results from specification-based expectations. Based on the recorded hardware specifications, the LX PRO should deliver substantially higher raw throughput in compute and rasterization, given its 4.1 times higher FP32 count, 6 times more shading units, and 3 times more ROPs. However, without benchmark scores, the database cannot confirm real-world performance.

For users requiring a low-power integrated solution that fits into mobile or compact systems, the 890M is the only option with validated scores. It delivers a PassMark G3D score of 8076 and a compute score of 4157, with a 15 W power draw. For users with a desktop chassis that can accommodate a dual-slot, 248 mm card with a 550 W power supply, the LX PRO offers 24 GB of GDDR6 and a 192-bit bus, which are specifications that no integrated part can match. The choice depends on whether the workload is constrained by power and space or by memory capacity and bandwidth. The data supports the 890M as a proven performer in its class, while the LX PRO remains an unverified entry with high specification ceilings.

FAQ

Q: What is the average benchmark score for the AMD Radeon 890M?

A: The recorded average benchmark score for the 890M is 9210, with a percentile rank of 45 among all GPUs.

Q: Does the Lisuan Tech LX PRO have any benchmark scores in the database?

A: No, the LX PRO has an empty benchmark array and an average score of 0, meaning no measured results are recorded.

Q: How does the 890M compare to its nearest rivals?

A: The 890M’s closest rival is the AMD Radeon Vega 8, which scores 9221 with a delta of -0.1%. The NVIDIA GeForce GTX 960 scores 9273 (-0.7%), the GTX 465 scores 9294 (-0.9%), and the GTX 850M scores 9302 (-1.0%). All deltas are negative, so the 890M trails each rival by less than 1%.

Q: What memory configuration does the Lisuan Tech LX PRO use?

A: The LX PRO uses 24 GB of GDDR6 memory on a 192-bit bus, with a bandwidth of 432.0 GB/s and an effective speed of 18 Gbps.

Q: What is the power consumption difference between the two devices?

A: The 890M has a TDP of 15 W and requires no power connectors, while the LX PRO has a TDP of 225 W and requires a 1x 16-pin power connector with a suggested power supply of 550 W.

Q: Which device supports a higher Vulkan version?

A: The AMD Radeon 890M supports Vulkan 1.4, while the Lisuan Tech LX PRO supports Vulkan 1.3.

Head-to-Head Benchmarks

Direct comparison is limited because the LX PRO has no recorded benchmark scores. The head-to-head benchmark array is empty, and the win counts are 0 for both devices. Therefore, the analysis must compare the 890M’s measured scores against the LX PRO’s specification-derived limits.

The 890M’s highest single-score result is 40808 in Geekbench Vulkan, followed by 37254 in Geekbench OpenCL. These scores reflect the 890M’s ability to execute compute and graphics workloads through modern APIs. In contrast, the LX PRO’s FP32 throughput of 24.58 TFLOPS suggests it would produce substantially higher raw compute scores, but no numbers exist to quantify the difference. The 890M’s FP32 is 5.939 TFLOPS, which is 24.2% of the LX PRO’s figure. If compute scaling were linear, the LX PRO would score roughly 4.1 times higher in pure FP32 workloads, but that extrapolation is not verified by the database.

In rasterization throughput, the LX PRO’s pixel rate of 192.0 GPixel/s is 2.07 times the 890M’s 92.80 GPixel/s. The texture rate of 384.0 GTexel/s is 2.07 times the 890M’s 185.6 GTexel/s. These ratios are identical because both devices have the same ratio of TMUs to ROPs: the 890M has 64 TMUs and 32 ROPs (2:1), and the LX PRO has 192 TMUs and 96 ROPs (2:1). The memory bandwidth gap is larger: the LX PRO’s 432.0 GB/s is not directly comparable to the 890M’s system-dependent bandwidth, but the 890M’s shared memory cannot match a dedicated 192-bit GDDR6 interface.

The 890M’s PassMark DirectX 9 score of 97 is its best legacy API result, and its DirectX 11 score of 73 is the next highest. The DirectX 12 score of 37 and DirectX 10 score of 33 are lower, which suggests that the 890M’s driver or hardware handles older APIs more efficiently. The LX PRO supports DirectX 12 Ultimate, and its architecture is unproven in legacy APIs. The database records no PassMark scores for the LX PRO, so no comparison is possible for those tests.

The 890M’s 3DMark Steel Nomad DX12 score is 590, which is a low result relative to its Geekbench scores. This indicates that the 890M struggles with modern, heavy DirectX 12 workloads. The LX PRO’s specifications, with 6 times more shading units and 3 times more ROPs, would likely produce a significantly higher Steel Nomad score, but again, no measured data exists.

The compute comparison is similarly one-sided on paper. The 890M’s PassMark GPU compute score is 4157, and its FP16 is equal to FP32 at 5.939 TFLOPS. The LX PRO’s FP16 is 49.15 TFLOPS with a 2:1 ratio, which is 8.3 times higher than the 890M’s FP16. For workloads that use FP16, the LX PRO’s advantage is larger than its FP32 advantage. The 890M’s 1:1 FP16 ratio means it does not gain throughput from half-precision operations, while the LX PRO effectively doubles its rate.

The only measured comparison available is the 890M against its nearest rivals, none of which is the LX PRO. The 890M’s average score of 9210 is 0.1% below the Vega 8, 0.7% below the GTX 960, 0.9% below the GTX 465, and 1.0% below the GTX 850M. These differences are within measurement noise, placing the 890M in the same performance class as those older discrete GPUs. The LX PRO, with a 225 W power budget and 24 GB of memory, targets a different class entirely, but the database has no scores to confirm its standing. The recorded data shows that the 890M is a validated, mid-pack performer, while the LX PRO remains an unmeasured specification sheet.