Intel Arc B770 vs Lisuan Tech LX ULTRA Comparison

Head-to-Head Benchmarks

The recorded database contains no direct benchmark scores for either the Intel Arc B770 or the Lisuan Tech LX ULTRA. The average benchmark score field for both entries is zero, and the head-to-head benchmark list is empty. The percentile versus all GPUs is identical for both parts at the 50th percentile, indicating that without measured data, both cards occupy the same neutral position in the overall distribution. This absence of test results means that no direct performance comparison can be drawn from the raw score data alone.

However, the specification sheets provide computable theoretical ceilings. The Intel Arc B770 delivers 19.66 TFLOPS of FP32 compute, while the Lisuan Tech LX ULTRA reaches 24.58 TFLOPS. That is a 25% advantage for the LX ULTRA in raw single-precision throughput. In FP16, the LX ULTRA produces 49.15 TFLOPS versus 39.32 TFLOPS for the Arc B770, a 25% lead as well. Pixel fill rate favors the Arc B770 at 307.2 GPixel/s against 192.0 GPixel/s, a 60% margin. Texture fill rate also favors Intel: 614.4 GTexel/s versus 384.0 GTexel/s, a 60% difference. Memory bandwidth goes to the Arc B770 with 512.0 GB/s versus 432.0 GB/s, an 18.5% advantage.

The LX ULTRA has more shading units (6144 versus 4096), but fewer texture mapping units (192 versus 256) and fewer raster output units (96 versus 128). This configuration explains the split: Lisuan prioritizes ALU-heavy work, while Intel allocates more fixed-function throughput per shader. The Arc B770 also has 32 dedicated ray tracing cores, while the LX ULTRA lists no ray tracing cores. The data suggests that in rasterization-bound tasks, the Arc B770 could sustain higher pixel and texture throughput, while in compute-heavy workloads, the LX ULTRA would likely execute more FP32 operations per cycle.

Because there are no measured game or application benchmarks, all comparative statements must be treated as architectural projections rather than verified results. The percentile field being identical at 50 for both cards indicates the database has not yet separated them by empirical performance.

Where Each One Wins

Based on the specification data, the Intel Arc B770 is positioned to win in scenarios that depend on pixel output, texture filtering, and memory bandwidth. Its 128 ROPs and 256 TMUs, combined with 512.0 GB/s of bandwidth, make it the stronger candidate for high-resolution rasterization, heavy post-processing effects, and texture-dense scenes. The 307.2 GPixel/s pixel rate is substantially higher than the LX ULTRA's 192.0 GPixel/s, which suggests better performance in fill-rate-limited situations such as 4K rendering with heavy anti-aliasing.

The Lisuan Tech LX ULTRA is positioned to win in compute-oriented workloads. Its 24.58 TFLOPS FP32 and 49.15 TFLOPS FP16 figures exceed the Arc B770 by 25% in both cases. Applications that scale with shader ALU count, such as physics simulation, AI inference (FP16), scientific computing, and certain rendering techniques like compute shaders, would likely benefit from the LX ULTRA's larger shader array of 6144 units. The 24 GB memory capacity also gives it a clear advantage in workloads that need large working sets, such as machine learning model training or large 3D scene caching.

The Arc B770's 16 GB frame buffer is smaller but paired with a 256-bit bus, yielding higher bandwidth. This makes it more suitable for real-time rendering at high resolutions where bandwidth is the bottleneck. The LX ULTRA's 192-bit bus and 432.0 GB/s bandwidth are lower, but the extra 8 GB of capacity could allow larger textures and geometry buffers without spilling to system memory.

For ray tracing, the Arc B770 has explicit RT cores (32 of them), while the LX ULTRA has none listed. This indicates the Arc B770 is the only one of the two with dedicated hardware acceleration for ray-traced effects. The LX ULTRA would have to rely on compute shaders for any ray tracing work, which is typically less efficient.

For connectivity, the Arc B770 offers both HDMI 2.1a and DisplayPort 2.1 outputs, while the LX ULTRA provides four DisplayPort 1.4a outputs. The Arc B770's DisplayPort 2.1 supports higher bandwidth for very high refresh rate or 8K displays, whereas the LX ULTRA's older DisplayPort 1.4a is limited to lower data rates.

Architecture Differences

The two GPUs come from different architectural lineages. The Intel Arc B770 uses the BMG-G31 chip based on the Xe2-HPG architecture, belonging to the Battlemage (Arc 7) generation. It is fabricated on a 5 nm process at TSMC with a die size of 368 mm². The Lisuan Tech LX ULTRA uses the 7G105 chip based on the TrueGPU architecture, belonging to the 7G100 generation. It is fabricated on a 6 nm process at TSMC, and its die size is unknown.

The process node difference is small: 5 nm versus 6 nm. The Arc B770's die area is recorded at 368 mm², while the LX ULTRA's die size is unknown, so no density comparison can be made. Transistor counts are unknown for both parts.

Memory subsystems differ in capacity and bus width. The Arc B770 uses 16 GB of GDDR6 on a 256-bit bus, achieving 512.0 GB/s. The LX ULTRA uses 24 GB of GDDR6 on a 192-bit bus, achieving 432.0 GB/s. The LX ULTRA has more memory but less bandwidth. The memory clock is listed as 2000 MHz (16 Gbps effective) for the Arc B770 and 2250 MHz (18 Gbps effective) for the LX ULTRA.

Compute resources differ significantly. The Arc B770 has 4096 shading units, 256 TMUs, 128 ROPs, and 32 RT cores. The LX ULTRA has 6144 shading units, 192 TMUs, 96 ROPs, and no listed RT cores. The LX ULTRA has 50% more shading units but 25% fewer TMUs and 25% fewer ROPs. The Arc B770 has dedicated ray tracing hardware, a feature the LX ULTRA lacks.

Both cards share the same 225 W TDP, dual-slot cooling footprint, PCIe 4.0 x16 interface, and 550 W suggested PSU. The power connectors differ: the Arc B770 uses a 1x 6-pin plus 1x 8-pin setup, while the LX ULTRA uses a single 16-pin connector.

API support shows a difference in Vulkan version. The Arc B770 supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The LX ULTRA supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.3. The Arc B770 has a newer Vulkan specification.

Physical dimensions are only recorded for the LX ULTRA: 268 mm in length, 112 mm in height, and 40 mm in width. The Arc B770's dimensions are not listed.

The LX ULTRA has an active production status and a release date of March 2026 (based on the timestamp). The Arc B770 has no production status listed and a release date of December 2025 (based on the timestamp). The Arc B770's predecessor is listed as Alchemist, while the LX ULTRA has no predecessor.

FAQ

Q: Which GPU has higher raw FP32 compute performance?

A: The Lisuan Tech LX ULTRA has 24.58 TFLOPS FP32, while the Intel Arc B770 has 19.66 TFLOPS FP32. The LX ULTRA leads by 25% in this metric.

Q: Which GPU has more memory and which has more bandwidth?

A: The Lisuan Tech LX ULTRA has 24 GB of GDDR6, while the Intel Arc B770 has 16 GB. However, the Arc B770 has higher memory bandwidth at 512.0 GB/s versus 432.0 GB/s due to its 256-bit bus compared to the LX ULTRA's 192-bit bus.

Q: Does either GPU have dedicated ray tracing hardware?

A: Only the Intel Arc B770 lists 32 ray tracing cores. The Lisuan Tech LX ULTRA has no ray tracing cores listed in its specifications.

Q: What are the power requirements for both cards?

A: Both cards have a 225 W TDP and require a 550 W suggested PSU. The Arc B770 uses one 6-pin and one 8-pin power connector, while the LX ULTRA uses a single 16-pin connector.

Q: Which GPU supports a newer version of Vulkan?

A: The Intel Arc B770 supports Vulkan 1.4, while the Lisuan Tech LX ULTRA supports Vulkan 1.3.

Q: Are there any measured benchmark scores for either GPU?

A: No. Both GPUs have an average benchmark score of zero, an empty benchmark list, and a percentile of 50 versus all GPUs. The head-to-head benchmark list is also empty.

The Verdict

Based strictly on the recorded data, the Intel Arc B770 is the better choice for rasterization-heavy rendering, high fill-rate scenarios, and ray-traced workloads. Its 60% higher pixel rate (307.2 GPixel/s versus 192.0 GPixel/s), 60% higher texture rate (614.4 GTexel/s versus 384.0 GTexel/s), and 18.5% higher memory bandwidth (512.0 GB/s versus 432.0 GB/s) make it the stronger performer for traditional game rendering, especially at high resolutions where bandwidth and fill rate dominate. The presence of 32 RT cores gives it a hardware advantage for ray tracing effects, which the LX ULTRA cannot match without dedicated acceleration.

The Lisuan Tech LX ULTRA is the better choice for compute-heavy applications that leverage massive shader arrays and large memory pools. Its 50% more shading units (6144 versus 4096) and 25% higher FP32 and FP16 throughput (24.58 TFLOPS and 49.15 TFLOPS versus 19.66 TFLOPS and 39.32 TFLOPS) indicate superior raw compute capability. The 24 GB memory capacity, 50% more than the Arc B770's 16 GB, supports larger datasets and textures. This makes it a more suitable option for AI inference, scientific computation, and content creation workloads that are not limited by pixel or texture throughput.

The choice depends entirely on the workload. For gaming and real-time graphics with ray tracing, the Arc B770's architecture is more balanced and better equipped. For parallel compute and memory-hungry tasks, the LX ULTRA's larger shader count and frame buffer provide a clear edge. Since no empirical benchmarks exist in the database, these conclusions are drawn from the architectural specifications alone.

Specification Differences

| Specification | Intel Arc B770 | Lisuan Tech LX ULTRA |

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

| Chip | BMG-G31 | 7G105 |

| Architecture | Xe2-HPG | TrueGPU |

| Generation | Battlemage (Arc 7) | 7G100 |

| Process Node | 5 nm | 6 nm |

| Die Size | 368 mm² | Unknown |

| Memory Size | 16 GB | 24 GB |

| Memory Bus Width | 256 bit | 192 bit |

| Memory Bandwidth | 512.0 GB/s | 432.0 GB/s |

| Memory Clock | 2000 MHz (16 Gbps effective) | 2250 MHz (18 Gbps effective) |

| Shading Units | 4096 | 6144 |

| TMUs | 256 | 192 |

| ROPs | 128 | 96 |

| Ray Tracing Cores | 32 | None |

| Pixel Rate | 307.2 GPixel/s | 192.0 GPixel/s |

| Texture Rate | 614.4 GTexel/s | 384.0 GTexel/s |

| FP32 Performance | 19.66 TFLOPS | 24.58 TFLOPS |

| FP16 Performance | 39.32 TFLOPS (2:1) | 49.15 TFLOPS (2:1) |

| Power Connectors | 1x 6-pin + 1x 8-pin | 1x 16-pin |

| Display Outputs | 1x HDMI 2.1a, 3x DisplayPort 2.1 | 4x DisplayPort 1.4a |

| Vulkan Support | 1.4 | 1.3 |

| Production Status | None listed | Active |

| Release Date | 2025-12-31 | 2026-03-16 |

| Dimensions | Not listed | 268 mm (L), 112 mm (H), 40 mm (W) |

Both cards share identical values for TDP (225 W), slot width (Dual-slot), suggested PSU (550 W), bus interface (PCIe 4.0 x16), DirectX support (12 Ultimate, 12_2), OpenGL support (4.6), memory type (GDDR6), foundry (TSMC), and transistor count (unknown). The launch MSRP is not listed for either product.