Intel Arc Pro B65 vs Lisuan Tech LX PRO Comparison

Architecture Differences

The Intel Arc Pro B65 and Lisuan Tech LX PRO represent two fundamentally different approaches to GPU design. The Intel part uses the BMG-G21 chip built on the Xe2-HPG architecture, part of the Battlemage (Pro Series) generation. It is fabricated on a 5 nm process at TSMC, with 19,600 million transistors packed into a 272 mm² die, yielding a transistor density of 72.1M per mm². The Lisuan Tech LX PRO, by contrast, uses the 7G105 chip based on the TrueGPU architecture from the 7G100 generation, manufactured on a 6 nm process, also at TSMC. Its transistor count and die size are recorded as unknown in the database, which limits direct density comparisons.

The core configurations differ sharply. The Intel Arc Pro B65 has 2,560 shading units, 160 texture mapping units, 80 render output units, and 20 ray tracing cores. The Lisuan Tech LX PRO carries 6,144 shading units, 192 TMUs, and 96 ROPs, but has no listed ray tracing cores, suggesting that ray tracing hardware is either absent or not disclosed. The shading unit count on the LX PRO is 2.4 times that of the Intel part, while its TMU and ROP counts are 1.2 times higher in each case. Despite this, both parts achieve identical pixel rates of 192.0 GPixel/s and identical texture rates of 384.0 GTexel/s, indicating that the Intel architecture's per-unit throughput compensates for its lower unit counts.

Compute throughput tells a similar story. The Intel Arc Pro B65 delivers 12.29 TFLOPS FP32 and 24.58 TFLOPS FP16 with a 2:1 ratio. The Lisuan Tech LX PRO delivers exactly double that: 24.58 TFLOPS FP32 and 49.15 TFLOPS FP16. The LX PRO's FP32 figure matches the Intel part's FP16 figure, which shows a substantial raw compute advantage for the Lisuan design. However, the Intel part includes dedicated ray tracing cores, a feature absent from the LX PRO's specifications, which matters for workloads that use hardware-accelerated ray tracing.

Memory architecture also diverges. The Intel Arc Pro B65 uses 32 GB of GDDR6 on a 256-bit bus, with memory clocks at 2375 MHz (19 Gbps effective) and bandwidth of 608.0 GB/s. The Lisuan Tech LX PRO uses 24 GB of GDDR6 on a 192-bit bus, with memory clocks at 2250 MHz (18 Gbps effective) and bandwidth of 432.0 GB/s. The Intel part holds a 33% bandwidth advantage, a 33% memory capacity advantage, and runs its memory at a slightly higher effective speed.

The bus interface differs as well: the Intel Arc Pro B65 uses PCIe 5.0 x16, while the Lisuan Tech LX PRO uses PCIe 4.0 x16. Display outputs also differ, with the Intel part offering four DisplayPort 2.1 connections versus the LX PRO's four DisplayPort 1.4a connections. API support is close, with both supporting DirectX 12 Ultimate (12_2) and OpenGL 4.6, but the Intel part supports Vulkan 1.4 while the LX PRO lists Vulkan 1.3.

FAQ

Q: Which GPU has more memory bandwidth?

A: The Intel Arc Pro B65 has 608.0 GB/s of bandwidth, which is 40.7% higher than the Lisuan Tech LX PRO's 432.0 GB/s. This comes from its wider 256-bit bus versus the LX PRO's 192-bit bus, despite the LX PRO using a slightly lower effective memory speed of 18 Gbps versus 19 Gbps.

Q: Is the Lisuan Tech LX PRO a faster compute part?

A: Based on recorded specifications, yes. The LX PRO delivers 24.58 TFLOPS FP32, exactly twice the Intel Arc Pro B65's 12.29 TFLOPS. Its FP16 output of 49.15 TFLOPS is also double the Intel part's 24.58 TFLOPS. The LX PRO also has more shading units (6,144 versus 2,560), more TMUs (192 versus 160), and more ROPs (96 versus 80).

Q: Which GPU supports ray tracing?

A: The Intel Arc Pro B65 has 20 dedicated ray tracing cores. The Lisuan Tech LX PRO lists no ray tracing cores in its specifications, which means hardware ray tracing support is not documented for that part.

Q: How do the power requirements compare?

A: The Intel Arc Pro B65 has a TDP of 200 W and uses a single 8-pin power connector. The Lisuan Tech LX PRO has a TDP of 225 W and uses a single 16-pin power connector. Both have a suggested PSU of 550 W and are dual-slot cards.

Q: Which card is physically larger?

A: The Lisuan Tech LX PRO is the only one with recorded dimensions: 248 mm in length, 118 mm in height, and 48 mm in width. The Intel Arc Pro B65 has no dimensions recorded in the database.

Q: What are the display output differences?

A: The Intel Arc Pro B65 provides four DisplayPort 2.1 outputs. The Lisuan Tech LX PRO provides four DisplayPort 1.4a outputs. The newer DisplayPort 2.1 standard on the Intel part supports higher bandwidth per connection.

The Verdict

The data presents a clear trade-off between compute throughput and memory resources. For workloads that are compute-bound, particularly FP32 or FP16 math without ray tracing, the Lisuan Tech LX PRO has a decisive advantage: it doubles the Intel Arc Pro B65's FP32 throughput (24.58 versus 12.29 TFLOPS) and doubles its FP16 throughput (49.15 versus 24.58 TFLOPS). Its larger shading unit count (6,144 versus 2,560) and higher TMU/ROP counts (192/96 versus 160/80) reinforce this lead, even though its pixel and texture rates match the Intel part exactly.

For memory-bound workloads, the Intel Arc Pro B65 is the stronger candidate. It offers 32 GB versus 24 GB of GDDR6, a 256-bit bus versus 192-bit, and 608.0 GB/s versus 432.0 GB/s of bandwidth. That 40.7% bandwidth advantage matters for large datasets, high-resolution textures, or workloads that stream significant data through memory. The Intel part also has a newer PCIe interface (5.0 x16 versus 4.0 x16), newer display outputs (DisplayPort 2.1 versus 1.4a), and the only dedicated ray tracing cores in this comparison.

The production status of both is Active, and both were released within the same month, the LX PRO on 2026-03-16 and the Intel part on 2026-03-31. Neither part has benchmark scores recorded in the database, so the verdict rests entirely on architectural specifications. The Lisuan Tech LX PRO is the compute-heavy option with a higher TDP (225 W versus 200 W) and a more power-hungry 16-pin connector. The Intel Arc Pro B65 is the memory-rich, feature-complete option with ray tracing, PCIe 5.0, and DisplayPort 2.1, at a lower 200 W TDP.

Head-to-Head Benchmarks

No direct benchmark scores are recorded in the database for either the Intel Arc Pro B65 or the Lisuan Tech LX PRO. The head-to-head benchmark table is empty, and neither GPU has any individual benchmark entries or nearest rival data. Consequently, the comparison below is derived from the recorded specification fields, which serve as the only measurable basis for evaluating these two parts.

The largest single-metric win for the Lisuan Tech LX PRO is in FP32 compute. Its 24.58 TFLOPS is exactly 100% higher than the Intel Arc Pro B65's 12.29 TFLOPS. This is the most dramatic gap in the entire comparison. The LX PRO also doubles the Intel part's FP16 output, moving from 24.58 to 49.15 TFLOPS. In shading units, the LX PRO's 6,144 count is 140% higher than the Intel part's 2,560. Its TMU count of 192 is 20% higher, and its ROP count of 96 is 20% higher.

The Intel Arc Pro B65's clearest wins are in memory and interface features. Its 608.0 GB/s bandwidth is 40.7% higher than the LX PRO's 432.0 GB/s. Its 32 GB memory capacity is 33.3% higher than 24 GB. Its memory bus width of 256 bits is 33.3% wider than 192 bits. The Intel part also uses a faster memory clock (2375 MHz versus 2250 MHz, or 19 Gbps versus 18 Gbps effective), a newer PCIe generation (5.0 x16 versus 4.0 x16), and a newer DisplayPort standard (2.1 versus 1.4a). The Intel part runs at a lower TDP of 200 W versus 225 W.

The two parts match exactly on several metrics: both achieve 192.0 GPixel/s pixel rate, both achieve 384.0 GTexel/s texture rate, both support DirectX 12 Ultimate (12_2) and OpenGL 4.6, both are dual-slot cards, and both have a suggested PSU of 550 W. They also share the same foundry (TSMC) and the same memory type (GDDR6).

One notable asymmetry is the transistor data. The Intel Arc Pro B65 has a fully documented die: 19,600 million transistors on 272 mm² with a density of 72.1M per mm². The Lisuan Tech LX PRO's transistor count and die size are unknown, which prevents a process-efficiency comparison. The Intel part's 5 nm process is one node ahead of the LX PRO's 6 nm process, but without the LX PRO's die data, the practical impact cannot be quantified.

The Intel Arc Pro B65's ray tracing cores (20) are unique to that part in this comparison. The LX PRO has no ray tracing core count listed. For any workload that relies on hardware ray tracing, the Intel part is the only one with documented support. Conversely, the LX PRO's lack of ray tracing cores may indicate a design focused purely on rasterized compute, which aligns with its doubled FP32 throughput.

Specification Differences

The table below lists only the fields where the two GPUs differ, based on the recorded data in the database.

| Specification | Intel Arc Pro B65 | Lisuan Tech LX PRO |

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

| Chip | BMG-G21 | 7G105 |

| Architecture | Xe2-HPG | TrueGPU |

| Generation | Battlemage (Pro Series) | 7G100 |

| Process node | 5 nm | 6 nm |

| Transistors | 19,600 million | unknown |

| Die size | 272 mm² | unknown |

| Transistor density | 72.1M / mm² | null |

| Base clock | 2400 MHz | null |

| Boost clock | 2400 MHz | null |

| Memory clock | 2375 MHz 19 Gbps effective | 2250 MHz 18 Gbps effective |

| Memory size | 32 GB | 24 GB |

| Memory bus width | 256 bit | 192 bit |

| Memory bandwidth | 608.0 GB/s | 432.0 GB/s |

| Shading units | 2560 | 6144 |

| TMUs | 160 | 192 |

| ROPs | 80 | 96 |

| RT cores | 20 | null |

| FP32 | 12.29 TFLOPS | 24.58 TFLOPS |

| FP16 | 24.58 TFLOPS (2:1) | 49.15 TFLOPS (2:1) |

| TDP | 200 W | 225 W |

| Power connectors | 1x 8-pin | 1x 16-pin |

| Bus interface | PCIe 5.0 x16 | PCIe 4.0 x16 |

| Display outputs | 4x DisplayPort 2.1 | 4x DisplayPort 1.4a |

| Vulkan version | 1.4 | 1.3 |

| Dimensions | null | 248 mm 9.8 inches length, 118 mm 4.6 inches height, 48 mm 1.9 inches width |

| Release date | 2026-03-31 | 2026-03-16 |

Fields that are identical between the two parts include: manufacturer foundry (TSMC), memory type (GDDR6), pixel rate (192.0 GPixel/s), texture rate (384.0 GTexel/s), slot width (Dual-slot), suggested PSU (550 W), DirectX support (12 Ultimate 12_2), OpenGL support (4.6), production status (Active), and the absence of a launch MSRP. Both GPUs also share the same 50th percentile versus all GPUs and an average benchmark score of 0, reflecting the absence of recorded benchmark data.