Intel Arc Pro B370 vs Lisuan Tech LX MAX Comparison

Intel Arc Pro B370 and Lisuan Tech LX MAX occupy opposite ends of the graphics hardware spectrum. The database records the Arc Pro B370 as an integrated graphics processor within Intel’s Panther Lake mobile platform, built on the Xe3-LPG architecture and produced on a 3 nm process at Intel’s own foundry. The Lisuan Tech LX MAX is a standalone dual-slot add-in board, fabricated by TSMC on a 6 nm process, using the TrueGPU architecture with the 7G106 chip. Their performance percentiles happen to coincide at the 50th mark against all GPUs in the database, but that shared percentile masks fundamentally different design targets. This analysis compares the two based on the recorded specifications, API support, and physical characteristics.

Where Each One Wins

The Intel Arc Pro B370 wins in integration and power efficiency. Its thermal design power is recorded at 25 W, compared to the LX MAX’s 225 W. That is a ninefold difference in power draw. The Arc Pro B370 uses system-shared memory, meaning it requires no dedicated VRAM allocation and fits into devices where space and cooling are constrained. Its bus interface is listed as IGP, so it connects directly to the host processor rather than through a PCIe slot. The slot width is recorded as IGP as well, with no power connectors required. This makes the Arc Pro B370 the only option of the two for ultra-thin portable devices, as its display outputs are described as portable device dependent. The LX MAX cannot operate in such an environment; it needs a PCIe 4.0 x16 slot, a dual-slot chassis position, a 16-pin power connector, and a recommended 550 W power supply.

The Lisuan Tech LX MAX wins in raw compute throughput and memory resources. Its FP32 performance is recorded at 24.58 TFLOPS, while the Arc Pro B370 delivers 6.144 TFLOPS. That places the LX MAX at four times the single-precision floating-point throughput. FP16 rates follow the same ratio: 49.15 TFLOPS versus 12.29 TFLOPS, both at a 2:1 ratio relative to FP32. The LX MAX also provides dedicated 12 GB of GDDR6 memory on a 192-bit bus, with 432.0 GB/s of bandwidth. The Arc Pro B370 has no dedicated memory at all; its bandwidth is listed as system dependent, and its memory clock is described as system shared. In any workload that stresses memory capacity or bandwidth, the LX MAX is the only viable choice.

Texture and pixel throughput follow the same pattern. The LX MAX records 384.0 GTexel/s and 192.0 GPixel/s, versus 96.00 GTexel/s and 48.00 GPixel/s for the Arc Pro B370. The LX MAX has 6144 shading units, 192 texture mapping units, and 96 render output units. The Arc Pro B370 has 1280 shading units, 40 TMUs, and 20 ROPs. The LX MAX leads by 4.8x in shading units, 4.8x in TMUs, and 4.8x in ROPs. These ratios align with the FP32 difference, confirming that the LX MAX is scaled proportionally across the entire rendering pipeline.

Ray tracing support exists on the Arc Pro B370, which records 10 dedicated ray tracing cores. The LX MAX has no listed RT core count. This is a notable differentiator: the integrated Intel part includes hardware acceleration for ray-traced effects, while the dedicated Lisuan board does not report such resources. For applications that rely on DirectX Raytracing or Vulkan ray tracing, the Arc Pro B370 has a functional advantage in feature set, if not in absolute speed.

FAQ

Q: Which GPU has higher raw compute performance?

A: The Lisuan Tech LX MAX. Its FP32 throughput is 24.58 TFLOPS, compared to 6.144 TFLOPS for the Intel Arc Pro B370. The LX MAX is exactly four times faster on this metric.

Q: Which GPU supports newer graphics APIs?

A: Both support DirectX 12 Ultimate (12_2) and OpenGL 4.6. The difference is in Vulkan: the Arc Pro B370 supports Vulkan 1.4, while the LX MAX supports Vulkan 1.3.

Q: Does the Intel Arc Pro B370 have dedicated video memory?

A: No. Its memory size, type, and bus width are all listed as system shared. The LX MAX has 12 GB of GDDR6 on a 192-bit bus with 432.0 GB/s bandwidth.

Q: What are the power requirements for each card?

A: The Arc Pro B370 is rated at 25 W TDP with no power connectors. The LX MAX is rated at 225 W TDP, requires a single 16-pin power connector, and the database recommends a 550 W power supply.

Q: Which GPU has more shading units?

A: The LX MAX has 6144 shading units. The Arc Pro B370 has 1280. The LX MAX also leads in texture mapping units (192 versus 40) and render output units (96 versus 20).

Q: Which GPU supports hardware ray tracing?

A: The Intel Arc Pro B370, which lists 10 ray tracing cores. The Lisuan Tech LX MAX does not list any ray tracing cores in the database.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark runs for these two products, and neither has recorded benchmark scores. The average benchmark score for both is zero, and there are no nearest rivals listed. However, the recorded specification data allows for a computed comparison of theoretical peak rates.

The largest single advantage for the LX MAX is in FP32 throughput. At 24.58 TFLOPS versus 6.144 TFLOPS, the LX MAX is 300% ahead of the Arc Pro B370. The same percentage gap appears in FP16, where 49.15 TFLOPS is 300% higher than 12.29 TFLOPS. These are the clearest metrics in the entire comparison, since they are direct arithmetic rates with no dependency on driver behavior or workload characteristics.

Pixel fill rate gives the LX MAX a 144.0 GPixel/s advantage. The LX MAX renders 192.0 GPixel/s, while the Arc Pro B370 renders 48.00 GPixel/s. In relative terms, the LX MAX is four times faster. Texture fill rate shows the same multiple: 384.0 GTexel/s versus 96.00 GTexel/s, a difference of 288.0 GTexel/s.

Memory bandwidth is another decisive margin. The LX MAX’s 432.0 GB/s is entirely absent on the Arc Pro B370, whose bandwidth is system dependent. In practice, the Arc Pro B370’s memory performance will vary with the host system’s RAM configuration, while the LX MAX has fixed GDDR6 bandwidth. This affects every workload that streams large textures or geometry.

Clock speeds do not directly compare because the LX MAX has no recorded base or boost clock. The Arc Pro B370 runs at a 300 MHz base and 2400 MHz boost. The LX MAX’s memory clock is recorded at 2250 MHz with 18 Gbps effective data rate. Without a core clock for the LX MAX, the performance ratios above are derived entirely from shader counts and throughput rates.

The one metric where the Arc Pro B370 leads is power efficiency per unit of compute. Dividing FP32 by TDP gives 0.246 TFLOPS per watt for the Arc Pro B370 and 0.109 TFLOPS per watt for the LX MAX. The Intel part delivers more than double the floating-point throughput per watt, despite having far lower absolute performance. This is consistent with the Arc Pro B370’s integrated design and the LX MAX’s high-power discrete configuration.

Specification Differences

The two products differ on nearly every physical and electrical specification. The Arc Pro B370 is an integrated GPU with an IGP bus interface and IGP slot width. The LX MAX is a dual-slot card with a PCIe 4.0 x16 interface. The Arc Pro B370 has no power connectors; the LX MAX uses a single 16-pin connector. The database lists no suggested power supply for the Arc Pro B370, while the LX MAX recommends 550 W.

Memory configuration is entirely different. The Arc Pro B370 uses system shared memory for size, type, bus width, and bandwidth. The LX MAX has 12 GB of GDDR6, a 192-bit bus, and 432.0 GB/s of bandwidth. Memory clocks also differ: the Arc Pro B370 lists system shared, while the LX MAX runs at 2250 MHz with 18 Gbps effective.

Compute unit counts diverge sharply. The Arc Pro B370 has 1280 shading units, 40 TMUs, 20 ROPs, and 10 RT cores. The LX MAX has 6144 shading units, 192 TMUs, and 96 ROPs, with no RT core count listed. The LX MAX has no tensor core count in either row.

Display outputs are another differentiator. The Arc Pro B370 uses portable device dependent outputs, reflecting its integration into laptops and handhelds. The LX MAX provides 4x DisplayPort 1.4a. The LX MAX also has recorded physical dimensions: 248 mm length, 118 mm height, and 48 mm width. The Arc Pro B370 has no recorded dimensions, consistent with its IGP form factor.

TDP is the most operationally significant difference. The Arc Pro B370 is rated at 25 W; the LX MAX at 225 W. This means the LX MAX requires active cooling and a substantial power supply, while the Arc Pro B370 can be passively cooled within a host device. The production status for both is active, but their release dates differ: the Arc Pro B370 is dated 2026-01-26, and the LX MAX is dated 2026-03-16.

Architecture Differences

The Intel Arc Pro B370 uses the Xe3-LPG architecture, part of the Arc Graphics-WM generation built around the Panther Lake chip. It is fabricated on a 3 nm process at Intel’s foundry. The LX MAX uses the TrueGPU architecture with the 7G106 chip, part of the 7G100 generation, fabricated on a 6 nm process at TSMC. These are fundamentally different design philosophies: Intel’s Xe3-LPG is a low-power graphics architecture aimed at integrated use, while TrueGPU appears to target high-throughput discrete rendering.

Transistor counts and die sizes are unknown for both products, so no comparison is possible on those metrics. The process node difference is significant: 3 nm versus 6 nm. The smaller Intel process allows for the Arc Pro B370’s low 25 W power envelope, while the larger TSMC node on the LX MAX supports a 225 W design.

Ray tracing support is an architectural differentiator. The Arc Pro B370 dedicates 10 cores to ray tracing, and its Vulkan support is version 1.4. The LX MAX has no RT core count and supports Vulkan 1.3. Both support DirectX 12 Ultimate at feature level 12_2 and OpenGL 4.6. The Arc Pro B370’s newer Vulkan version indicates a more recent driver stack or hardware feature set.

The memory architecture reflects the product class. The Arc Pro B370 depends on the host system’s memory, with bandwidth varying by platform. The LX MAX has a fixed GDDR6 subsystem with 432.0 GB/s bandwidth, isolated from host memory performance. This architectural choice gives the LX MAX predictable memory behavior across all systems, while the Arc Pro B370’s memory performance is system dependent.

The LX MAX’s pixel and texture rates are exactly four times those of the Arc Pro B370, matching the shader count ratio. This consistency suggests the two architectures scale similarly in terms of per-shader output, despite their different nodes and origins. The Arc Pro B370’s ray tracing cores provide a feature that the LX MAX does not report, but the LX MAX’s raw throughput is in a different performance class entirely.

The release date gap of roughly seven weeks places the LX MAX after the Arc Pro B370 in the database’s timeline. Both are listed as active production parts. The Arc Pro B370 has a predecessor recorded as HD Graphics-WM, while the LX MAX has no predecessor. No successors are listed for either product.