Intel Arc Pro B70 vs Lisuan Tech LX 7G100 Comparison

Intel Arc Pro B70 and Lisuan Tech LX 7G100 are two discrete graphics cards with fundamentally different design priorities. The recorded data shows that neither card has a completed benchmark suite, with both showing an average benchmark score of zero and a percentile rank of 50 against all GPUs. The head-to-head benchmark table is empty, so no direct performance comparisons from standardized tests exist in the database. This analysis relies entirely on the architectural and specification fields to interpret what each card is designed to do.

Head-to-Head Benchmarks

The database contains no recorded benchmark results for either the Intel Arc Pro B70 or the Lisuan Tech LX 7G100. The head-to-head benchmark list is empty, and both cards have zero wins recorded in the winsA and winsB fields. This means that no measured performance data from standardized workloads, synthetic tests, or game benchmarks is available for either product.

Without recorded scores, the only quantitative comparison comes from the raw compute and throughput figures in the specification tables. The Lisuan Tech LX 7G100 delivers a higher FP32 throughput at 24.58 TFLOPS compared to the Intel Arc Pro B70 at 22.94 TFLOPS. That is a 1.64 TFLOPS advantage for the Lisuan card, which translates to roughly 7% higher raw single-precision compute. The FP16 figures follow the same pattern, with the Lisuan card at 49.15 TFLOPS versus the Intel card at 45.88 TFLOPS, again a 2:1 ratio for both.

The Intel Arc Pro B70 counters with significantly higher pixel and texture throughput. Its pixel rate is 358.4 GPixel/s, which is 166.4 GPixel/s higher than the Lisuan card's 192.0 GPixel/s. The texture rate shows a similar gap: 716.8 GTexel/s for Intel versus 384.0 GTexel/s for Lisuan. These differences indicate that the Intel card has a wider memory interface and more render output units, which directly influence fill-rate-heavy workloads.

Memory bandwidth also favors Intel. The Arc Pro B70 has 608.0 GB/s of bandwidth from a 256-bit bus with 32 GB of GDDR6, while the Lisuan card has 432.0 GB/s from a 192-bit bus with 12 GB. That is a 176.0 GB/s difference, or roughly 41% more bandwidth for the Intel card. The Lisuan card, however, has a higher memory clock at 2250 MHz (18 Gbps effective) versus 2375 MHz (19 Gbps effective) for Intel, but the narrower bus negates that advantage.

The shading unit count is where Lisuan leads. The LX 7G100 has 6144 shading units, while the Arc Pro B70 has 4096. The Intel card has more texture mapping units (256 versus 192) and more raster operation units (128 versus 96). The Lisuan card also has no recorded ray tracing core count, while the Intel card has 32 RT cores.

FAQ

Q: Which card has higher raw FP32 compute?

A: The Lisuan Tech LX 7G100 has a higher FP32 throughput at 24.58 TFLOPS, compared to the Intel Arc Pro B70 at 22.94 TFLOPS. The Lisuan card also leads in FP16 at 49.15 TFLOPS versus 45.88 TFLOPS.

Q: How do the memory subsystems differ?

A: The Intel Arc Pro B70 has 32 GB of GDDR6 on a 256-bit bus, delivering 608.0 GB/s of bandwidth. The Lisuan Tech LX 7G100 has 12 GB of GDDR6 on a 192-bit bus, delivering 432.0 GB/s. The Intel card has a 176.0 GB/s bandwidth advantage.

Q: Which card has a higher pixel fill rate?

A: The Intel Arc Pro B70 has a pixel rate of 358.4 GPixel/s, which is substantially higher than the Lisuan card's 192.0 GPixel/s. The Intel card also has a texture rate of 716.8 GTexel/s versus 384.0 GTexel/s for Lisuan.

Q: What process nodes do the two cards use?

A: The Intel Arc Pro B70 uses a 5 nm process from TSMC, while the Lisuan Tech LX 7G100 uses a 6 nm process, also from TSMC. The Intel card has a die size of 368 mm², while the Lisuan die size is unknown.

Q: Do both cards support the same API levels?

A: Both cards support DirectX 12 Ultimate (12_2) and OpenGL 4.6. The Intel card supports Vulkan 1.4, while the Lisuan card supports Vulkan 1.3. The Intel card also has 32 ray tracing cores, while the Lisuan card has no recorded RT core count.

Q: What are the power requirements for each card?

A: The Intel Arc Pro B70 has a TDP of 230 W and a suggested PSU of 550 W. The Lisuan Tech LX 7G100 has a TDP of 225 W and also a suggested PSU of 550 W. Both use a single 8-pin power connector.

Architecture Differences

The Intel Arc Pro B70 is built on the Xe2-HPG architecture, specifically the BMG-G31 chip, and belongs to the Battlemage Pro Series generation. The Lisuan Tech LX 7G100 uses a different architecture called TrueGPU, with the chip designator 7G106 and a generation name of 7G100. These are distinct architectural families with different design goals.

The process nodes differ. Intel uses a 5 nm TSMC process, while Lisuan uses a 6 nm TSMC process. The Intel die is 368 mm², but the Lisuan die size is not recorded. Transistor counts are unknown for both cards.

The core organization is significantly different. The Intel card has 4096 shading units, 256 TMUs, 128 ROPs, and 32 RT cores. The Lisuan card has 6144 shading units, 192 TMUs, and 96 ROPs, but no RT core count is specified. This suggests the Lisuan architecture focuses on raw shading throughput rather than dedicated ray tracing hardware.

The memory architecture also differs. Intel uses a 256-bit bus with 32 GB of GDDR6 at 2375 MHz (19 Gbps effective). Lisuan uses a 192-bit bus with 12 GB of GDDR6 at 2250 MHz (18 Gbps effective). The Intel card has higher total bandwidth at 608.0 GB/s versus 432.0 GB/s.

The API support shows a slight difference in Vulkan versions. Intel supports Vulkan 1.4, while Lisuan supports Vulkan 1.3. Both support DirectX 12 Ultimate (12_2) and OpenGL 4.6.

The bus interface differs. Intel uses PCIe 5.0 x16, while Lisuan uses PCIe 4.0 x16. This affects potential data transfer rates between the CPU and GPU, though no measured bandwidth figures are recorded.

Specification Differences

The Intel Arc Pro B70 has a base clock of 2280 MHz and a boost clock of 2800 MHz. The Lisuan Tech LX 7G100 has no recorded base or boost clocks, only a memory clock of 2250 MHz. The Intel card's memory clock is 2375 MHz.

Memory capacity is a major difference: 32 GB for Intel versus 12 GB for Lisuan. The bus width is 256-bit for Intel and 192-bit for Lisuan. Bandwidth is 608.0 GB/s versus 432.0 GB/s.

The shading unit count is 4096 for Intel and 6144 for Lisuan. Texture mapping units are 256 for Intel and 192 for Lisuan. Raster operation units are 128 for Intel and 96 for Lisuan. The Intel card has 32 RT cores, while the Lisuan card has no recorded RT cores.

Pixel rate is 358.4 GPixel/s for Intel and 192.0 GPixel/s for Lisuan. Texture rate is 716.8 GTexel/s for Intel and 384.0 GTexel/s for Lisuan. FP32 is 22.94 TFLOPS for Intel and 24.58 TFLOPS for Lisuan. FP16 is 45.88 TFLOPS for Intel and 49.15 TFLOPS for Lisuan.

The TDP is 230 W for Intel and 225 W for Lisuan. Both use a single 8-pin power connector and suggest a 550 W PSU. Both are dual-slot cards.

The display outputs differ. Intel has 1x HDMI 2.1a and 3x DisplayPort 2.1. Lisuan has 4x DisplayPort 1.4a. The Intel card supports newer display standards.

Physical dimensions vary. Intel is 267 mm long, 110 mm high, and 39 mm wide. Lisuan is 294 mm long, 120 mm high, and 49 mm wide. The Lisuan card is larger in all dimensions.

The bus interface is PCIe 5.0 x16 for Intel and PCIe 4.0 x16 for Lisuan. The process node is 5 nm for Intel and 6 nm for Lisuan. The die size is 368 mm² for Intel and unknown for Lisuan.

The production status is not recorded for Intel, while Lisuan is marked as Active. The release dates differ: Intel on 2026-03-25 and Lisuan on 2026-06-17.

The Intel card has a launch MSRP of 949 USD, while the Lisuan card has no recorded launch MSRP.

Where Each One Wins

The Intel Arc Pro B70 wins in memory capacity and bandwidth. With 32 GB of GDDR6 on a 256-bit bus, it delivers 608.0 GB/s, which is substantially higher than the Lisuan card's 12 GB and 432.0 GB/s. This makes the Intel card better suited for workloads that need large datasets resident in VRAM, such as high-resolution rendering, complex scenes, or multi-model inference.

The Intel card also wins in pixel and texture throughput. Its pixel rate of 358.4 GPixel/s is nearly double the Lisuan card's 192.0 GPixel/s. The texture rate of 716.8 GTexel/s is also nearly double the Lisuan card's 384.0 GTexel/s. This indicates the Intel card is stronger for fill-rate-bound tasks, such as high-resolution rasterization with heavy overdraw or texture-heavy shading.

The Intel card has dedicated ray tracing cores (32 RT cores), while the Lisuan card has no recorded RT core count. This suggests the Intel card is better for ray-traced effects, though no benchmark data confirms actual performance.

The Intel card supports PCIe 5.0 x16, while the Lisuan card uses PCIe 4.0 x16. The newer interface provides higher theoretical bandwidth for data transfers, though no measured figures are available.

The Lisuan Tech LX 7G100 wins in raw compute throughput. Its FP32 rate of 24.58 TFLOPS is higher than the Intel card's 22.94 TFLOPS. The FP16 rate of 49.15 TFLOPS also exceeds the Intel card's 45.88 TFLOPS. This makes the Lisuan card potentially better for compute-heavy workloads that rely on shading unit throughput, such as general-purpose GPU computing.

The Lisuan card has more shading units at 6144 versus 4096 for Intel. This higher count aligns with its higher FP32 output. The Lisuan card also has a lower TDP at 225 W versus 230 W for Intel, meaning it delivers more FP32 per watt based on the recorded figures.

The Lisuan card has a newer production status of Active, while Intel's status is not recorded. This suggests the Lisuan card is currently in production.

The Lisuan card has a 6 nm process node versus 5 nm for Intel. The larger process node may imply different manufacturing costs, but no pricing data is available beyond the Intel launch MSRP.

The Verdict

The Intel Arc Pro B70 is the choice for workloads that demand high memory capacity and bandwidth. The data shows 32 GB of VRAM and 608.0 GB/s of bandwidth, which supports large datasets and high-resolution textures. The pixel rate of 358.4 GPixel/s and texture rate of 716.8 GTexel/s indicate strong fill-rate performance for rasterization-heavy tasks. The presence of 32 RT cores suggests ray tracing capability, though no benchmark confirms this. The newer PCIe 5.0 interface and DisplayPort 2.1 outputs also position this card for modern systems.

The Lisuan Tech LX 7G100 is the choice for compute-heavy workloads that prioritize raw shading throughput. The FP32 rate of 24.58 TFLOPS and FP16 rate of 49.15 TFLOPS are higher than the Intel card. The 6144 shading units outnumber the Intel card's 4096. The lower TDP of 225 W versus 230 W means the Lisuan card achieves higher throughput with slightly lower power draw. The smaller memory capacity of 12 GB and lower bandwidth of 432.0 GB/s limit its use in memory-intensive tasks, but the compute advantage stands.

Users who require massive VRAM for large model training or rendering scenes with high geometric complexity should select the Intel Arc Pro B70. Its 32 GB capacity and 608.0 GB/s bandwidth are the highest recorded figures in this comparison. The pixel and texture rates also favor Intel for high-resolution output.

Users who run compute kernels that are not memory-bound, such as certain simulation or inference workloads, may prefer the Lisuan Tech LX 7G100. Its higher FP32 and FP16 throughput, combined with more shading units, indicates superior raw compute capability. The lack of RT cores and lower memory bandwidth are limitations, but the compute figures are unambiguous.

Neither card has recorded benchmark scores, so these conclusions rest entirely on specification-derived analysis. The percentile rank of 50 for both cards is a placeholder until actual performance data is logged. The release dates show the Intel card arrived first on 2026-03-25, followed by the Lisuan card on 2026-06-17. The Intel card has a launch MSRP of 949 USD, while the Lisuan card's price is not recorded. Without measured performance, the choice between these two cards depends on whether memory capacity and fill-rate or raw compute throughput is the higher priority.