AMD Radeon AI PRO R9700S vs Lisuan Tech LX PRO Comparison

FAQ

Q: What are the core architectural differences between the AMD Radeon AI PRO R9700S and the Lisuan Tech LX PRO?

A: The AMD card uses the Navi 48 chip built on RDNA 4.0 architecture with a 4 nm process, while the Lisuan Tech LX PRO uses the 7G105 chip built on TrueGPU architecture with a 6 nm process. Both are manufactured by TSMC.

Q: How do the memory configurations compare?

A: The AMD Radeon AI PRO R9700S has 32 GB of GDDR6 memory on a 256 bit bus with 644.6 GB/s bandwidth. The Lisuan Tech LX PRO has 24 GB of GDDR6 memory on a 192 bit bus with 432.0 GB/s bandwidth.

Q: Which card has higher raw FP32 compute performance?

A: The AMD Radeon AI PRO R9700S delivers 47.84 TFLOPS FP32, which is nearly double the 24.58 TFLOPS FP32 of the Lisuan Tech LX PRO.

Q: What are the power requirements for each card?

A: The AMD Radeon AI PRO R9700S has a TDP of 300 W and suggests a 700 W PSU. The Lisuan Tech LX PRO has a TDP of 225 W and suggests a 550 W PSU. Both use a single 16-pin power connector.

Q: How do the display outputs differ?

A: The AMD Radeon AI PRO R9700S provides 4x DisplayPort 2.1a outputs. The Lisuan Tech LX PRO provides 4x DisplayPort 1.4a outputs.

Q: What are the physical dimensions of each card?

A: The AMD card measures 267 mm in length, 109 mm in height, and 39 mm in width. The Lisuan Tech LX PRO measures 248 mm in length, 118 mm in height, and 48 mm in width. Both are dual-slot cards.

Architecture Differences

The AMD Radeon AI PRO R9700S is built around the Navi 48 chip with RDNA 4.0 architecture, part of the Radeon Pro Navi (Navi IV Series) generation. The chip is manufactured on a 4 nm process at TSMC with 53,900 million transistors on a 357 mm² die, yielding a transistor density of 151.0M per mm². The Lisuan Tech LX PRO uses the 7G105 chip with TrueGPU architecture from the 7G100 generation, manufactured on a 6 nm process at TSMC. Transistor count and die size for the Lisuan part are not recorded.

The AMD card implements 64 dedicated ray tracing cores, while the Lisuan card has no recorded ray tracing core count. The AMD GPU also supports a newer PCIe interface: PCIe 5.0 x16 versus PCIe 4.0 x16 on the Lisuan card. On the API front, both support DirectX 12 Ultimate (12_2) and OpenGL 4.6, but the AMD card supports Vulkan 1.4 while the Lisuan card supports Vulkan 1.3.

The compute resource distribution differs substantially. The AMD card uses 4096 shading units with 256 texture mapping units and 128 ROPs. The Lisuan card uses 6144 shading units, which is 50% more, but pairs them with only 192 TMUs and 96 ROPs, both lower than the AMD card. The higher shading unit count on the Lisuan card does not translate into higher FP32 throughput because the recorded FP32 figure is 24.58 TFLOPS versus 47.84 TFLOPS on the AMD card.

The FP16 ratio also differs. The AMD card achieves FP16 at a 1:1 ratio with FP32, meaning 47.84 TFLOPS FP16. The Lisuan card achieves FP16 at a 2:1 ratio, delivering 49.15 TFLOPS FP16, which is slightly higher than the AMD card's FP16 output despite the AMD card having nearly double the FP32 performance. This indicates a different compute focus: the AMD card balances FP32 and FP16 workloads evenly, while the Lisuan card prioritizes FP16 throughput.

The memory subsystem follows a similar divergence. The AMD card uses a 256 bit bus with 32 GB of GDDR6 and 644.6 GB/s of bandwidth. The Lisuan card uses a 192 bit bus with 24 GB of GDDR6 and 432.0 GB/s of bandwidth. The AMD card thus provides 33% more memory capacity and roughly 49% more bandwidth.

Where Each One Wins

The AMD Radeon AI PRO R9700S wins in scenarios that depend on raw FP32 compute, memory bandwidth, and large memory capacity. Its 47.84 TFLOPS FP32 and 644.6 GB/s bandwidth make it the stronger choice for FP32-heavy workloads such as scientific simulation, engineering analysis, and general purpose GPU compute. The 32 GB frame buffer also supports larger datasets and higher resolution textures without spilling to system memory.

The Lisuan Tech LX PRO wins in scenarios that leverage FP16 throughput. Its 49.15 TFLOPS FP16 exceeds the AMD card's 47.84 TFLOPS FP16, making it competitive for mixed-precision workloads that rely on FP16 accumulation. The lower TDP of 225 W and suggested PSU of 550 W also make it less demanding on system power delivery.

The AMD card wins on display interface modernity with DisplayPort 2.1a support, which permits higher bandwidth per display connection compared to DisplayPort 1.4a on the Lisuan card. The AMD card also wins on pixel fill rate at 373.8 GPixel/s versus 192.0 GPixel/s, and on texture fill rate at 747.5 GTexel/s versus 384.0 GTexel/s.

The Lisuan card wins on physical compactness in length, at 248 mm versus 267 mm for the AMD card, but it is taller and wider. The Lisuan card also wins on FP16 performance and on lower system power requirements.

Specification Differences

The two cards differ across nearly every recorded specification category. The AMD card uses a 4 nm process with 53,900 million transistors on a 357 mm² die, while the Lisuan card uses a 6 nm process with unknown transistor count and die size. The AMD card has a base clock of 1660 MHz, a boost clock of 2920 MHz, and a game clock of 2350 MHz. The Lisuan card has no recorded base, boost, or game clocks. The AMD memory clock is 2518 MHz (20.1 Gbps effective), and the Lisuan memory clock is 2250 MHz (18 Gbps effective).

Memory capacity differs: 32 GB on the AMD card versus 24 GB on the Lisuan card. Bus width differs: 256 bit versus 192 bit. Bandwidth differs: 644.6 GB/s versus 432.0 GB/s. Shading units differ: 4096 versus 6144. TMUs differ: 256 versus 192. ROPs differ: 128 versus 96. Ray tracing cores are present on the AMD card at 64, and absent from the recorded data on the Lisuan card.

Pixel rate is 373.8 GPixel/s on the AMD card versus 192.0 GPixel/s on the Lisuan card. Texture rate is 747.5 GTexel/s versus 384.0 GTexel/s. FP32 is 47.84 TFLOPS versus 24.58 TFLOPS. FP16 is 47.84 TFLOPS (1:1) versus 49.15 TFLOPS (2:1). TDP is 300 W versus 225 W. Suggested PSU is 700 W versus 550 W. Bus interface is PCIe 5.0 x16 versus PCIe 4.0 x16. Display outputs are 4x DisplayPort 2.1a versus 4x DisplayPort 1.4a. Vulkan support is 1.4 versus 1.3.

Physical dimensions differ as well. The AMD card is 267 mm long, 109 mm tall, and 39 mm wide. The Lisuan card is 248 mm long, 118 mm tall, and 48 mm wide. Both are dual-slot and both use a single 16-pin power connector. The AMD card has a recorded release date of 2025-12-10, while the Lisuan card has a recorded release date of 2026-03-16. The AMD card lists the Radeon Pro Vega as its predecessor, while the Lisuan card has no predecessor recorded.

Head-to-Head Benchmarks

The head-to-head benchmark data set contains no recorded entries, so the comparison relies on the specification-derived performance metrics in the database. The largest recorded advantage for the AMD Radeon AI PRO R9700S appears in FP32 compute, where 47.84 TFLOPS is roughly 95% higher than the 24.58 TFLOPS of the Lisuan Tech LX PRO. This is the single biggest performance gap between the two cards.

The AMD card also holds a substantial lead in memory bandwidth at 644.6 GB/s versus 432.0 GB/s, a difference of approximately 49%. Pixel fill rate favors the AMD card by a wide margin: 373.8 GPixel/s versus 192.0 GPixel/s, which is roughly 95% higher. Texture fill rate follows the same pattern: 747.5 GTexel/s versus 384.0 GTexel/s, again roughly 95% higher.

The one recorded metric where the Lisuan card takes the lead is FP16 compute. The Lisuan card delivers 49.15 TFLOPS FP16, which is about 3% higher than the AMD card's 47.84 TFLOPS FP16. This is a narrow margin, but it is the only compute metric where the Lisuan card registers a win.

The AMD card also leads in memory clock speed at 2518 MHz versus 2250 MHz, and in memory capacity at 32 GB versus 24 GB. The Lisuan card leads in shading unit count at 6144 versus 4096, but this does not translate into higher FP32 throughput, indicating lower per-shader efficiency in the recorded data.

Both cards are recorded with an average benchmark score of 0 and a percentile versus all GPUs of 50, meaning the database has no empirical benchmark results for either card. The specification-level analysis therefore provides the only available comparison. The AMD card's higher ROP count (128 versus 96) and higher TMU count (256 versus 192) reinforce its advantage in fill-rate-bound workloads. The Lisuan card's higher shading unit count suggests a design aimed at wide parallel execution, but the recorded FP32 figure does not support that design being effective for FP32 work.

The Verdict

The recorded data places the AMD Radeon AI PRO R9700S ahead in most compute and memory metrics. Its 47.84 TFLOPS FP32, 644.6 GB/s bandwidth, and 32 GB memory capacity make it the stronger candidate for FP32-heavy compute, high-resolution rendering, and large dataset processing. The 64 ray tracing cores give it a hardware feature that the Lisuan card lacks in the record. The DisplayPort 2.1a outputs and PCIe 5.0 x16 interface also position it as the more modern platform.

The Lisuan Tech LX PRO holds a narrow FP16 advantage at 49.15 TFLOPS versus 47.84 TFLOPS, and it requires less power at 225 W versus 300 W. It also uses a shorter PCB at 248 mm versus 267 mm. For workloads that are strictly FP16-bound and power constrained, the Lisuan card offers a viable alternative. However, the FP16 gap is small, and the AMD card's advantages in FP32, bandwidth, fill rates, and memory capacity are substantially larger in magnitude.

The database shows no empirical benchmark scores for either card, so the verdict is based entirely on the recorded specifications. The AMD card is the more capable overall GPU according to the data, with higher throughput in most measured categories. The Lisuan card is the more efficient choice in terms of power draw and the only card with a higher FP16 figure, but its FP32 performance is less than half of the AMD card's, and its memory bandwidth is roughly one third lower. Users prioritizing FP32 compute, large memory, or modern display connectivity should select the AMD Radeon AI PRO R9700S. Users prioritizing FP16 throughput or lower system power requirements should consider the Lisuan Tech LX PRO.