Intel Arc Pro B390 vs Lisuan Tech LX ULTRA Comparison

FAQ

Q: What are the fundamental differences in how the Intel Arc Pro B390 and Lisuan Tech LX ULTRA are manufactured?

A: The Intel Arc Pro B390 uses a 3 nm process node fabricated by Intel, while the Lisuan Tech LX ULTRA uses a 6 nm process node fabricated by TSMC.

Q: What type of memory does each GPU use?

A: The Intel Arc Pro B390 uses system shared memory, with memory type, bus width, and bandwidth all listed as system dependent. The Lisuan Tech LX ULTRA uses 24 GB of GDDR6 memory on a 192-bit bus, delivering 432.0 GB/s of bandwidth.

Q: How do the two GPUs differ in terms of physical installation?

A: The Intel Arc Pro B390 is an integrated graphics processor (IGP) with no power connectors and a slot width of IGP. The Lisuan Tech LX ULTRA is a dual-slot add-in card that is 268 mm long, 112 mm high, and 40 mm wide, requiring a single 16-pin power connector and a suggested 550 W power supply.

Q: Which GPU has higher raw compute throughput?

A: The Lisuan Tech LX ULTRA delivers 24.58 TFLOPS of FP32 compute and 49.15 TFLOPS of FP16 compute (2:1), while the Intel Arc Pro B390 delivers 7.680 TFLOPS of FP32 and 15.36 TFLOPS of FP16 (2:1).

Q: Do both GPUs support the same graphics APIs?

A: Both support DirectX 12 Ultimate (12_2) and OpenGL 4.6. The Intel Arc Pro B390 supports Vulkan 1.4, while the Lisuan Tech LX ULTRA supports Vulkan 1.3.

Q: What is the thermal design power of each GPU?

A: The Intel Arc Pro B390 has a TDP of 80 W, while the Lisuan Tech LX ULTRA has a TDP of 225 W.

Where Each One Wins

The recorded data separates these two GPUs into very different usage profiles. The Intel Arc Pro B390, as an IGP, is designed for portable device dependent display output and consumes only 80 W. Its 300 MHz base clock and 2500 MHz boost clock operate within a tight power envelope. The Lisuan Tech LX ULTRA, by contrast, is a dual-slot discrete card with its own 24 GB GDDR6 frame buffer and 432.0 GB/s of bandwidth.

For memory-bound workloads, the LX ULTRA wins decisively. The 192-bit bus and dedicated GDDR6 memory are not dependent on system memory performance, unlike the B390's system shared memory. The LX ULTRA's 432.0 GB/s bandwidth is a fixed specification, whereas the B390's bandwidth is system dependent. Applications that repeatedly access large datasets, such as high-resolution texture streaming or large framebuffer operations, favor the discrete card.

For compute-heavy tasks, the LX ULTRA's shading unit count of 6144, TMUs of 192, and ROPs of 96 more than triple the B390's 1536 shading units, 48 TMUs, and 24 ROPs. The FP32 throughput of 24.58 TFLOPS versus 7.680 TFLOPS indicates the LX ULTRA handles parallel floating-point workloads at roughly three times the rate. Pixel rate and texture rate follow the same pattern: 192.0 GPixel/s versus 60.00 GPixel/s, and 384.0 GTexel/s versus 120.0 GTexel/s.

The B390 wins on integration and power. As an IGP, it requires no additional slot, no power connectors, and draws 80 W. Systems using it avoid the 225 W TDP and 550 W suggested PSU of the LX ULTRA. The B390 also supports Vulkan 1.4, a newer API revision than the LX ULTRA's Vulkan 1.3.

Architecture Differences

The Intel Arc Pro B390 is built on the Xe3-LPG architecture and belongs to the Arc Graphics-WM (Panther Lake) generation, using the Panther Lake chip. It is fabricated on a 3 nm process at Intel. The architecture integrates 12 RT cores, a feature absent from the LX ULTRA's specification sheet, which lists no RT core count. The B390's predecessor is listed as HD Graphics-WM.

The Lisuan Tech LX ULTRA uses the TrueGPU architecture with the 7G105 chip, belonging to the 7G100 generation. It is fabricated on a 6 nm process at TSMC. The LX ULTRA has no listed RT cores and no listed tensor cores, matching the B390 in the latter category as the B390 also has no listed tensor cores. Both GPUs have unknown transistor counts and die sizes.

The B390's memory subsystem is entirely system shared, with the memory clock and bandwidth described as system dependent. The LX ULTRA operates its GDDR6 memory at 2250 MHz with 18 Gbps effective speed. The B390 is an IGP with a bus interface of IGP, while the LX ULTRA uses PCIe 4.0 x16.

The display output configurations differ substantially. The B390's display outputs are portable device dependent, reflecting its integrated nature. The LX ULTRA provides 4x DisplayPort 1.4a outputs, a fixed configuration for multi-monitor setups.

Specification Differences

The clock behavior differs: the B390 has a base clock of 300 MHz and a boost clock of 2500 MHz, while the LX ULTRA has no listed base or boost clock. The memory clock for the LX ULTRA is 2250 MHz (18 Gbps effective); the B390's memory clock is system shared.

Memory capacity and type: the B390 uses system shared memory with no dedicated size, while the LX ULTRA has 24 GB of GDDR6. Bus width: the B390 is system shared, the LX ULTRA is 192 bit. Bandwidth: the B390 is system dependent, the LX ULTRA is 432.0 GB/s.

Compute resources: the B390 has 1536 shading units, 48 TMUs, and 24 ROPs. The LX ULTRA has 6144 shading units, 192 TMUs, and 96 ROPs. The B390 has 12 RT cores; the LX ULTRA has no RT core count listed.

Fill rates: the B390 produces 60.00 GPixel/s and 120.0 GTexel/s. The LX ULTRA produces 192.0 GPixel/s and 384.0 GTexel/s. FP32: 7.680 TFLOPS versus 24.58 TFLOPS. FP16: 15.36 TFLOPS versus 49.15 TFLOPS, both at a 2:1 ratio.

Power and physical: the B390 has an 80 W TDP, IGP slot width, and no power connectors. The LX ULTRA has a 225 W TDP, dual-slot width, one 16-pin power connector, and a suggested PSU of 550 W. The B390 measures no listed dimensions; the LX ULTRA measures 268 mm by 112 mm by 40 mm.

API support: both share DirectX 12 Ultimate (12_2) and OpenGL 4.6. The B390 supports Vulkan 1.4; the LX ULTRA supports Vulkan 1.3. The B390's bus interface is IGP; the LX ULTRA's is PCIe 4.0 x16.

Release dates: the B390 released on 2026-01-26, the LX ULTRA on 2026-03-16. Both have a production status of Active. Neither has a launch MSRP listed.

Head-to-Head Benchmarks

The database contains no recorded head-to-head benchmark entries, and both GPUs have an average benchmark score of 0 with a percentile of 50 against all GPUs. The winsA and winsB counters are both 0. Without direct benchmark measurements, the comparison relies on the specification-based throughput figures.

The largest specification gap is in FP32 compute. The LX ULTRA's 24.58 TFLOPS is 220% higher than the B390's 7.680 TFLOPS. In FP16, the LX ULTRA's 49.15 TFLOPS is 220% higher than the B390's 15.36 TFLOPS. These ratios match the shading unit ratio: 6144 divided by 1536 equals 4, and the TFLOPS ratio is 24.58 divided by 7.680 which equals 3.2, so the per-shader efficiency favors the B390 slightly, but the absolute throughput strongly favors the LX ULTRA.

Pixel throughput shows a 3.2x advantage for the LX ULTRA: 192.0 GPixel/s versus 60.00 GPixel/s. Texture throughput also shows a 3.2x advantage: 384.0 GTexel/s versus 120.0 GTexel/s. These ratios are consistent with the ROP and TMU counts: 96 divided by 24 equals 4 for ROPs, and 192 divided by 48 equals 4 for TMUs, meaning per-unit efficiency is slightly higher on the B390, but the LX ULTRA's raw counts dominate.

Memory bandwidth cannot be compared as a ratio because the B390's bandwidth is system dependent. The LX ULTRA's fixed 432.0 GB/s stands as the only recorded bandwidth figure. The B390's memory size is also system dependent, while the LX ULTRA's 24 GB is fixed.

The B390's advantage lies in its 80 W TDP versus 225 W, and its IGP form factor versus a dual-slot, 268 mm card. The B390 also carries 12 RT cores, which the LX ULTRA does not list. The B390's Vulkan 1.4 support is one revision newer than the LX ULTRA's Vulkan 1.3.

The Verdict

The Lisuan Tech LX ULTRA is the stronger performer in every measured throughput category. Its 24.58 TFLOPS FP32, 432.0 GB/s memory bandwidth, 24 GB GDDR6, and 192.0 GPixel/s pixel rate position it for workloads that demand sustained compute and memory throughput. The 225 W TDP and 550 W suggested PSU indicate a system built around a discrete, high-power card, and its 4x DisplayPort 1.4a outputs support multi-display configurations.

The Intel Arc Pro B390 serves a different role. Its 80 W TDP, IGP slot width, no power connectors, and portable device dependent display outputs fit systems where power and space are constrained. The 12 RT cores provide ray tracing capability that the LX ULTRA does not list. Vulkan 1.4 support is the newer API revision.

The data does not support a single winner across all use cases. The LX ULTRA is the choice for raw performance, memory capacity, and fixed bandwidth. The B390 is the choice for integrated, low-power systems with ray tracing support and the latest Vulkan revision. The lack of recorded benchmark scores and head-to-head results means the comparison is defined entirely by specification data, which consistently favors the LX ULTRA in throughput and the B390 in power efficiency and integration.