Intel Arc Graphics 64EU vs Lisuan Tech LX MAX Comparison

Where Each One Wins

The recorded data splits these two graphics solutions into entirely different usage categories. The Intel Arc Graphics 64EU is an integrated graphics processor (IGP) embedded in the Arrow Lake-S chip, designed for systems where a separate graphics card is not installed. Its single recorded benchmark result, a 3DMark Steel Nomad DX12 score of 733, places it at the 3rd percentile of all GPUs in the database. That percentile ranking indicates it sits near the very bottom of the performance distribution, suitable only for basic desktop workloads, legacy applications, or very light gaming at low settings.

The Lisuan Tech LX MAX, by contrast, is a discrete, dual-slot add-in board with its own 12 GB of GDDR6 memory on a 192-bit bus. It carries a 225 W TDP and requires a 16-pin power connector plus a 550 W suggested power supply. Its percentile ranking of 50 places it exactly at the median of all GPUs in the database, meaning it outperforms roughly half of all recorded graphics hardware. The LX MAX has no recorded benchmark entries in the database, so its wins cannot be quantified from direct measurements, but its specifications alone indicate it is built for demanding graphical workloads where the Arc 64EU would be inadequate.

The use-case split is therefore stark. The Intel part wins in scenarios where power draw, system simplicity, and zero additional hardware are the priorities. It needs no power connectors, occupies no expansion slot, and consumes only 65 W. The Lisuan part wins wherever raw throughput, dedicated memory, and sustained rendering performance matter, such as modern gaming, content creation, or compute tasks that can use its 24.58 TFLOPS of FP32 throughput.

Architecture Differences

The architectural gap between these two parts is fundamental. Intel uses the Xe-LPG architecture on TSMC's 3 nm process, built around the Arrow Lake-S chip with 17,800 million transistors on a 243 mm² die. That yields a transistor density of 73.3 million transistors per square millimeter. The Lisuan Tech LX MAX uses a "TrueGPU" architecture on TSMC's 6 nm process, with unspecified transistor count and die size. The process node difference alone, 3 nm versus 6 nm, explains why Intel can pack far more transistors into a smaller area, though the LX MAX compensates with a much larger absolute configuration.

The execution resources differ by an order of magnitude. Intel's 64EU part has 512 shading units, 32 texture mapping units, and 16 render output units. The Lisuan part has 6144 shading units, 192 TMUs, and 96 ROPs. That is 12 times more shaders, 6 times more TMUs, and 6 times more ROPs. Pixel rate for the LX MAX is 192.0 GPixel/s versus 30.40 GPixel/s for the Intel part. Texture rate is 384.0 GTexel/s versus 60.80 GTexel/s. FP32 compute is 24.58 TFLOPS versus 1.946 TFLOPS, a 12.6x advantage. FP16 compute is 49.15 TFLOPS versus 3.891 TFLOPS, both using a 2:1 ratio.

Memory architecture is also completely different. The Intel part uses system shared memory, meaning it borrows from the host CPU's RAM. Its memory clock, bus width, and bandwidth are all listed as "System Shared" or "System Dependent". The LX MAX has dedicated 12 GB GDDR6 running at 2250 MHz with an 18 Gbps effective rate, on a 192-bit bus, delivering 432.0 GB/s of bandwidth. That dedicated memory eliminates contention with the CPU and provides predictable, high-bandwidth access for graphics data.

Clock behavior differs as well. Intel lists a base clock of 300 MHz and a boost clock of 1900 MHz. The LX MAX has no base or boost clock listed in the database, only its memory clock. The Intel part integrates into the Ring Bus interface, while the LX MAX uses PCIe 4.0 x16. Display outputs differ: Intel relies on motherboard-dependent outputs, while the LX MAX provides 4x DisplayPort 1.4a connectors.

API support is nearly identical. Both support DirectX 12 Ultimate (12_2) and OpenGL 4.6. The Intel part supports Vulkan 1.4, while the LX MAX supports Vulkan 1.3. Neither lists dedicated ray tracing cores or tensor cores in the database.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark entries for these two products. The wins counter shows 0 for both sides. This is an unusual situation, but the nearest-rival data for the Intel part provides a reference frame. The Intel Arc Graphics 64EU scores 733 in 3DMark Steel Nomad DX12, identical to the Intel Arc Graphics 32EU and Intel Arc Graphics 24EU, both also at 733 with a 0% delta. That parity across Intel's own integrated lineup suggests the 64EU configuration does not meaningfully separate itself from lower EU counts in this particular test, likely due to shared memory bandwidth or thermal constraints.

The AMD Radeon HD 6470M scores 723, which is 1.4% behind the Intel part. The NVIDIA GeForce GT 415M scores 751, which is 2.4% ahead. These are ancient mobile discrete GPUs, and the Intel IGP essentially trades blows with them. That context reinforces the 3rd percentile ranking: the Intel part is competitive with hardware from over a decade ago, not with modern discrete solutions.

For the LX MAX, the absence of any benchmark scores or nearest rivals in the database means its actual measured performance cannot be compared numerically to the Intel part. The data does show its theoretical rates: 192.0 GPixel/s, 384.0 GTexel/s, 24.58 TFLOPS FP32. Using those figures against the Intel part's measured rates, the LX MAX is 6.3x faster in pixel throughput and 6.3x faster in texture throughput. Its FP32 compute is 12.6x higher. These are specification-derived ratios, not benchmark deltas, but they are the only quantitative comparisons the database supports.

The Intel part's 733 score at 30.40 GPixel/s and 60.80 GTexel/s implies that doubling or tripling those rates would still not approach the LX MAX's theoretical ceiling. The LX MAX's 192.0 GPixel/s pixel rate is a figure that the Intel part cannot reach under any recorded condition, because the Intel part's ROP count and clock are fixed.

FAQ

Q: Which part has more shading units?

A: The Lisuan Tech LX MAX has 6144 shading units, while the Intel Arc Graphics 64EU has 512. That is a 12x difference.

Q: Does the Intel Arc Graphics 64EU have dedicated memory?

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

Q: What is the performance percentile of each part?

A: The Intel Arc Graphics 64EU sits at the 3rd percentile of all GPUs in the database. The Lisuan Tech LX MAX sits at the 50th percentile.

Q: Which part supports a newer Vulkan version?

A: The Intel Arc Graphics 64EU supports Vulkan 1.4. The Lisuan Tech LX MAX supports Vulkan 1.3.

Q: What is the TDP difference?

A: The Intel part is rated at 65 W. The Lisuan part is rated at 225 W and requires a 550 W suggested power supply.

Q: Are there any direct benchmark comparisons in the database?

A: No. The database lists zero head-to-head benchmark entries, and the LX MAX has no recorded benchmark scores at all.

The Verdict

The data directs each part to a distinct audience. The Intel Arc Graphics 64EU is for systems that will never install a discrete GPU. Its 3rd percentile ranking and its parity with the Intel Arc Graphics 32EU and 24EU indicate that its 512 shading units and 1.946 TFLOPS are sufficient only for basic graphical output, not for serious rendering. Its nearest rivals are the AMD Radeon HD 6470M and NVIDIA GeForce GT 415M, both obsolete mobile parts, and it trades within a few percent of them. That comparison alone tells the story: the Intel IGP is a fallback option, not a performance component.

The Lisuan Tech LX MAX is for systems that demand dedicated resources. Its 50th percentile ranking means it sits in the middle of the entire GPU landscape, which is a far stronger position than the Intel part. Its 12 GB GDDR6, 432.0 GB/s bandwidth, and 24.58 TFLOPS FP32 are figures that belong to a discrete, high-power card. The 225 W TDP and dual-slot form factor confirm it is designed for installation in a PCIe 4.0 x16 slot with a 16-pin power connector, not for integration into a motherboard.

Who should pick which follows directly from the recorded specifications. A user with a slim desktop or an all-in-one system that cannot accept a dual-slot card has no choice but the Intel IGP. A user with a standard ATX case, a 550 W or better power supply, and workloads that use 3D acceleration will pick the LX MAX. The 12.6x FP32 advantage and 6.3x pixel rate advantage leave no ambiguity about which part delivers more graphics work per unit time.

The lack of direct benchmarks for the LX MAX is a limitation in the database, but the specification gap is so wide that measured results would almost certainly confirm the same conclusion. The Intel part's only recorded score, 733 in Steel Nomad, is a low bar that the LX MAX's theoretical rates suggest it would clear by a wide margin. The verdict is not a close call. It is a split by design: integrated for convenience, discrete for performance.

Specification Differences

| Field | Intel Arc Graphics 64EU | Lisuan Tech LX MAX |

|-------|-------------------------|---------------------|

| Manufacturer | Intel | Unknown |

| Chip | Arrow Lake-S | 7G106 |

| Architecture | Xe-LPG | TrueGPU |

| Generation | Arc Graphics (Arrow Lake) | 7G100 |

| Process node | 3 nm | 6 nm |

| Foundry | TSMC | TSMC |

| Transistors | 17,800 million | unknown |

| Die size | 243 mm² | unknown |

| Transistor density | 73.3M / mm² | null |

| Base clock | 300 MHz | null |

| Boost clock | 1900 MHz | null |

| Memory clock | System Shared | 2250 MHz 18 Gbps effective |

| Memory size | System Shared | 12 GB |

| Memory type | System Shared | GDDR6 |

| Memory bus width | System Shared | 192 bit |

| Memory bandwidth | System Dependent | 432.0 GB/s |

| Shading units | 512 | 6144 |

| TMUs | 32 | 192 |

| ROPs | 16 | 96 |

| Pixel rate | 30.40 GPixel/s | 192.0 GPixel/s |

| Texture rate | 60.80 GTexel/s | 384.0 GTexel/s |

| FP32 | 1.946 TFLOPS | 24.58 TFLOPS |

| FP16 | 3.891 TFLOPS (2:1) | 49.15 TFLOPS (2:1) |

| TDP | 65 W | 225 W |

| Slot width | IGP | Dual-slot |

| Power connectors | null | 1x 16-pin |

| Suggested PSU | null | 550 W |

| Bus interface | Ring Bus | PCIe 4.0 x16 |

| Display outputs | Motherboard Dependent | 4x DisplayPort 1.4a |

| Vulkan | 1.4 | 1.3 |

| Dimensions (length) | null | 248 mm 9.8 inches |

| Dimensions (height) | null | 118 mm 4.6 inches |

| Dimensions (width) | null | 48 mm 1.9 inches |

| Release date | 2024-10-23 | 2026-03-16 |

| Predecessor | HD Graphics | null |

| Average benchmark score | 733 | 0 |

| Percentile vs all GPUs | 3 | 50 |