Intel Arc B390 vs Lisuan Tech LX ULTRA Comparison

The Intel Arc B390 and Lisuan Tech LX ULTRA occupy opposite ends of the hardware spectrum. The Arc B390 is an integrated graphics processor (IGP) built for portable devices, while the LX ULTRA is a massive dual-slot add-in board with dedicated memory. Their recorded data shows almost no overlap in purpose, yet comparing them clarifies what each architecture prioritizes.

Where Each One Wins

The Intel Arc B390 wins in scenarios where power draw and physical footprint are the limiting factors. Its 80 W TDP and IGP slot width mean it requires no power connectors and no expansion slot. The database lists its display outputs as "Portable Device Dependent," which confirms its target environment: laptops and compact systems where a discrete card cannot fit. Its 3 nm process node, built by Intel, allows this level of integration.

The Lisuan Tech LX ULTRA wins in raw throughput and memory capacity. It delivers 24.58 TFLOPS of FP32 compute, 432.0 GB/s of memory bandwidth, and 24 GB of GDDR6 memory on a 192 bit bus. The Arc B390 manages 7.680 TFLOPS and relies on System Shared memory with System Dependent bandwidth. In any workload that stresses sustained compute or large data sets, the LX ULTRA dominates.

The use-case split is stark. The Arc B390 suits the mobile and embedded space. The LX ULTRA suits desktop workstations with a PCIe 4.0 x16 slot, a 550 W suggested PSU, and a 1x 16-pin power connector. The dual-slot cooler and 268 mm length indicate a card designed for unrestricted airflow. The Arc B390, by contrast, has no cooler of its own; it lives on the motherboard.

Benchmark coverage also differs. The Arc B390 has one recorded 3DMark Steel Nomad DX12 score of 1482. The LX ULTRA has no recorded benchmark scores, so its wins are theoretical, based on specifications rather than measured results.

Architecture Differences

The two chips share nothing architecturally. The Arc B390 uses the Xe3-LPG architecture on Intel's Panther Lake chip. Its process node is 3 nm, fabricated by Intel. The LX ULTRA uses the TrueGPU architecture with the 7G105 chip, built on a 6 nm process at TSMC.

Shader resources diverge heavily. The Arc B390 has 1536 shading units, 48 texture mapping units, and 24 ROPs. The LX ULTRA has 6144 shading units, 192 TMUs, and 96 ROPs. That is exactly 4 times the shading units, 4 times the TMUs, and 4 times the ROPs. The LX ULTRA also has 12 ray tracing cores on the Arc side, while the LX ULTRA lists no RT core count at all. The Arc B390 has no tensor core count listed; the LX ULTRA also lists none.

Clock behavior differs. The Arc B390 has a base clock of 300 MHz and a boost clock of 2500 MHz. The LX ULTRA has no base or boost clock listed. Instead, its memory runs at 2250 MHz with 18 Gbps effective speed. The Arc B390 uses System Shared memory with no dedicated bus width, while the LX ULTRA has a 192 bit bus.

API support is close but not identical. Both support DirectX 12 Ultimate (12_2) and OpenGL 4.6. The Arc B390 supports Vulkan 1.4; the LX ULTRA supports Vulkan 1.3. The LX ULTRA has four DisplayPort 1.4a outputs, while the Arc B390's display outputs are portable-device dependent.

Pixel and texture rates reflect the scale difference. The Arc B390 produces 60.00 GPixel/s and 120.0 GTexel/s. The LX ULTRA produces 192.0 GPixel/s and 384.0 GTexel/s. FP16 rates follow the same 2:1 ratio pattern: 15.36 TFLOPS for the Arc, 49.15 TFLOPS for the LX ULTRA.

The LX ULTRA is a dual-slot card measuring 268 mm by 112 mm by 40 mm. The Arc B390 has no listed dimensions because it is an IGP. Power delivery is equally divergent: the Arc uses none, the LX ULTRA requires a 16-pin connector and a 550 W PSU.

Head-to-Head Benchmarks

The database contains no head-to-head benchmark entries between these two products. The only measured score belongs to the Arc B390: 1482 in 3DMark Steel Nomad DX12. That score places it in the 9th percentile of all GPUs. Its nearest rivals in the database are older NVIDIA parts: the GeForce GT 520MX with an average score of 1463, the GeForce 800M at 1460, the GeForce GT 625 OEM at 1446, and the GeForce GT 710 at 1443.

The deltas are small. The Arc B390 leads the GT 520MX by 1.3%, the GeForce 800M by 1.5%, the GT 625 OEM by 2.5%, and the GT 710 by 2.7%. These are not large margins. The Arc B390 sits just above a cluster of low-end discrete GPUs from a previous era, which is notable for an integrated solution.

The LX ULTRA has no benchmark scores in the database. Its average benchmark score is recorded as 0, and its percentile versus all GPUs is 50. With no measured data, any head-to-head comparison must rely on the statistical position and the raw specification sheet. The 50th percentile placement suggests the database estimates it as a midrange performer, but this is not backed by a recorded test run.

Certain wins are predictable from the data. In FP32 throughput, the LX ULTRA delivers 24.58 TFLOPS versus 7.680 TFLOPS, a 3.2x advantage. In texture rate, 384.0 GTexel/s versus 120.0 GTexel/s is exactly 3.2x. Pixel rate shows 192.0 GPixel/s versus 60.00 GPixel/s, again 3.2x. The ratio holds across the board because the LX ULTRA scales shader, TMU, and ROP counts uniformly.

Memory is the largest practical divide. The LX ULTRA has 24 GB of GDDR6 with 432.0 GB/s bandwidth. The Arc B390 has System Shared memory, meaning it borrows from the host system's RAM. Its bandwidth is listed as System Dependent, so no fixed number exists. In memory-heavy tasks, the LX ULTRA's dedicated pool avoids contention with the CPU.

The Arc B390's only measured benchmark places it just ahead of the GT 710, which is a card from a much older generation. That is a modest result. The LX ULTRA, with 24.58 TFLOPS and a 50th percentile standing, should outperform it by a wide margin in any compute-bound test, but the absence of recorded scores prevents a direct confirmation.

The Verdict

The data supports a clear split. For systems with a PCIe 4.0 x16 slot, a 550 W PSU, and room for a 268 mm dual-slot card, the Lisuan Tech LX ULTRA is the only choice. It offers 24 GB of GDDR6, 432.0 GB/s of bandwidth, 24.58 TFLOPS, and a 3.2x advantage in pixel and texture rates over the Arc B390. Its 50th percentile ranking and 6 nm TSMC process position it as a midrange discrete part.

For portable devices, the Intel Arc B390 is the only option that fits. It consumes 80 W, uses no power connectors, and routes display output through the host device. Its 1482 Steel Nomad score and 9th percentile ranking indicate entry-level performance, but it outperforms older low-end discrete cards like the GT 710 by 2.7%. That is a meaningful result for an IGP.

Users who need ray tracing should note the Arc B390 lists 12 RT cores, while the LX ULTRA lists none. The Arc B390 also supports Vulkan 1.4, one version ahead of the LX ULTRA's 1.3. These are narrow advantages for the mobile part.

Users who need raw compute, large memory pools, or sustained bandwidth should choose the LX ULTRA. The 24 GB GDDR6 frame buffer is 24 GB more than the Arc's shared memory. The 192 bit bus and 432.0 GB/s bandwidth are fixed figures, whereas the Arc's bandwidth is system dependent.

The LX ULTRA's lack of recorded benchmarks is a limitation. Its 50th percentile and zero average score indicate the database has not yet run it, so its real-world standing remains unverified. The Arc B390, by contrast, has one verified result. Any user relying on measured data should treat the LX ULTRA's specifications as provisional.

FAQ

Q: Which GPU has the higher FP32 compute?

A: The Lisuan Tech LX ULTRA delivers 24.58 TFLOPS, while the Intel Arc B390 delivers 7.680 TFLOPS. The LX ULTRA's figure is 3.2 times higher.

Q: How much memory does each GPU have?

A: The LX ULTRA has 24 GB of GDDR6 on a 192 bit bus with 432.0 GB/s bandwidth. The Arc B390 uses System Shared memory with System Dependent bandwidth.

Q: What is the Arc B390's measured benchmark score?

A: The Arc B390 scores 1482 in 3DMark Steel Nomad DX12. This places it in the 9th percentile of all GPUs.

Q: Does the LX ULTRA have any recorded benchmark scores?

A: No. The database lists no benchmarks for the LX ULTRA, and its average benchmark score is recorded as 0. Its percentile versus all GPUs is 50.

Q: Which GPU supports a newer Vulkan version?

A: The Intel Arc B390 supports Vulkan 1.4. The Lisuan Tech LX ULTRA supports Vulkan 1.3.

Q: What are the power requirements for each?

A: The Arc B390 has an 80 W TDP and no power connectors. The LX ULTRA has a 225 W TDP, requires one 16-pin power connector, and lists a 550 W suggested PSU.

Specification Differences

| Specification | Intel Arc B390 | Lisuan Tech LX ULTRA |

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

| Chip | Panther Lake | 7G105 |

| Architecture | Xe3-LPG | TrueGPU |

| Generation | Arc Graphics-M (Panther Lake) | 7G100 |

| Process Node | 3 nm | 6 nm |

| Foundry | Intel | TSMC |

| Base Clock | 300 MHz | None listed |

| Boost Clock | 2500 MHz | None listed |

| Memory Clock | System Shared | 2250 MHz, 18 Gbps effective |

| Memory Size | System Shared | 24 GB |

| Memory Type | System Shared | GDDR6 |

| Memory Bus Width | System Shared | 192 bit |

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

| Shading Units | 1536 | 6144 |

| TMUs | 48 | 192 |

| ROPs | 24 | 96 |

| RT Cores | 12 | None listed |

| Pixel Rate | 60.00 GPixel/s | 192.0 GPixel/s |

| Texture Rate | 120.0 GTexel/s | 384.0 GTexel/s |

| FP32 | 7.680 TFLOPS | 24.58 TFLOPS |

| FP16 | 15.36 TFLOPS (2:1) | 49.15 TFLOPS (2:1) |

| TDP | 80 W | 225 W |

| Slot Width | IGP | Dual-slot |

| Power Connectors | None | 1x 16-pin |

| Suggested PSU | None listed | 550 W |

| Bus Interface | IGP | PCIe 4.0 x16 |

| Display Outputs | Portable Device Dependent | 4x DisplayPort 1.4a |

| Vulkan | 1.4 | 1.3 |

| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |

| OpenGL | 4.6 | 4.6 |

| Dimensions | None listed | 268 mm, 112 mm, 40 mm |

| Release Date | 2026-01-26 | 2026-03-16 |

| Avg Benchmark Score | 1482 | 0 |

| Percentile vs All GPUs | 9 | 50 |