Intel Arc Pro B390 vs Intel Graphics 24EU Mobile Comparison

Where Each One Wins

The recorded data for the Intel Arc Pro B390 and the Intel Graphics 24EU Mobile shows a clear separation of roles, though neither part has a populated benchmark suite in the database. Based purely on the architectural and specification data, the Arc Pro B390 dominates in every measurable compute and graphics capability. The Graphics 24EU Mobile, by contrast, is defined by its minimal resource footprint and extremely low power envelope.

The Arc Pro B390 wins decisively on raw throughput. Its FP32 compute of 7.680 TFLOPS is twenty times the 384.0 GFLOPS of the Graphics 24EU Mobile. Texture rate follows the same pattern: 120.0 GTexel/s versus 12.00 GTexel/s, a factor of ten. Pixel rate comes in at 60.00 GPixel/s versus 4.000 GPixel/s, representing a fifteen-fold difference. These are not marginal advantages; they place the Arc Pro B390 in a completely different performance class.

The Graphics 24EU Mobile wins on power efficiency and integration simplicity. Its TDP is 6 W, which is a thirteenth of the 80 W TDP of the Arc Pro B390. The bus interface is listed as Ring Bus, while the Arc Pro B390 uses an IGP interface. For a low-power mobile part, the Ring Bus connection reflects a design that prioritizes minimal complexity and system integration cost over high-bandwidth data movement.

The Arc Pro B390 also holds the feature advantage in ray tracing. It includes 12 RT cores, while the Graphics 24EU Mobile lists no RT cores at all. This makes the Arc Pro B390 the only one of the two that can realistically handle hardware-accelerated ray tracing workloads. Similarly, the DirectX support differs: the Arc Pro B390 supports 12 Ultimate (12_2), while the Graphics 24EU Mobile only reaches DirectX 12 (12_1). The newer API tier matters for games and applications that use mesh shaders, variable rate shading, and other DX12 Ultimate features.

In terms of architecture generation, the Arc Pro B390 uses Xe3-LPG on a 3 nm process, while the Graphics 24EU Mobile uses Xe-LP on a 10 nm process. The process node difference is significant for density and power characteristics, though neither part lists transistor counts or die sizes in the database. The Arc Pro B390 also carries a higher boost clock of 2500 MHz versus 1000 MHz for the Graphics 24EU Mobile, with both sharing a 300 MHz base clock.

Architecture Differences

The two GPUs come from different Intel graphics families and target different system roles. The Arc Pro B390 is built on the Panther Lake chip with the Xe3-LPG architecture, belonging to the Arc Graphics-WM generation. The Graphics 24EU Mobile uses the Twin Lake chip with the Xe-LP architecture, part of the HD Graphics-T generation. These are separate design lineages with different priorities.

The shading unit count tells the core story. The Arc Pro B390 has 1536 shading units, while the Graphics 24EU Mobile has 192. That is an eight-to-one ratio. Texture mapping units follow a four-to-one ratio: 48 versus 12. Render output units are even more skewed: 24 versus 4, a six-to-one ratio. The Arc Pro B390 also has 12 RT cores; the Graphics 24EU Mobile has none.

The memory subsystem is listed as System Shared for both parts, with System Dependent bandwidth. This means neither GPU has dedicated VRAM, and performance will scale with the host memory configuration. The bus width is also System Shared for both, so the database does not record a fixed memory interface width. The Arc Pro B390 uses an IGP bus interface, while the Graphics 24EU Mobile uses a Ring Bus interface.

Clock behavior differs substantially. Both start at 300 MHz base, but the Arc Pro B390 boosts to 2500 MHz, while the Graphics 24EU Mobile tops out at 1000 MHz. The higher boost clock on the Arc Pro B390, combined with its larger execution resource pool, produces the massive throughput gap seen in the pixel, texture, and FP32 rates.

The process nodes are 3 nm for the Arc Pro B390 and 10 nm for the Graphics 24EU Mobile. Both are fabricated by Intel, according to the foundry field. The 3 nm process gives the Arc Pro B390 a density and power advantage per transistor, though the database does not list transistor counts or die sizes for either part.

API support is mostly aligned. Both support OpenGL 4.6 and Vulkan 1.4. The difference is in DirectX: the Arc Pro B390 supports 12 Ultimate (12_2), while the Graphics 24EU Mobile is limited to 12 (12_1). This means the Arc Pro B390 can run applications that require the full DX12 Ultimate feature set, including hardware ray tracing and mesh shaders.

The power envelope is a major differentiator. The Arc Pro B390 has an 80 W TDP and no power connectors, indicating it is an integrated part designed for a high-performance mobile platform. The Graphics 24EU Mobile has a 6 W TDP, making it suitable for very low-power, always-on or entry-level mobile devices. The slot width for both is listed as IGP, meaning neither is a discrete card.

The Verdict

The data indicates the Intel Arc Pro B390 is the superior GPU in every recorded performance metric. Its 1536 shading units, 12 RT cores, 2500 MHz boost clock, and 7.680 TFLOPS FP32 rate place it in a different tier from the Graphics 24EU Mobile. The Arc Pro B390 also has a more advanced 3 nm process node, newer Xe3-LPG architecture, and DirectX 12 Ultimate support. For any workload that demands compute throughput, texture filtering, pixel fill, or ray tracing, the Arc Pro B390 is the only viable choice of the two.

The Intel Graphics 24EU Mobile is not without its niche. Its 6 W TDP is drastically lower than the 80 W of the Arc Pro B390. The Ring Bus interface suggests a simpler integration path. The 192 shading units and 1000 MHz boost clock are sufficient for basic display output and light 2D workloads. The database does not record any benchmark scores for either part, so the performance comparison relies entirely on specifications.

The choice between the two should be driven by the host platform. The Arc Pro B390 belongs in a system that can supply 80 W to the GPU and that benefits from high FP32 throughput, ray tracing, and DX12 Ultimate features. The Graphics 24EU Mobile belongs in a power-constrained device where the GPU is a secondary concern and the primary goal is minimal power draw and simple integration.

No pricing information is available in the database for either part, so no cost-based comparison is possible. The release dates differ: the Arc Pro B390 is dated 2026-01-26, while the Graphics 24EU Mobile is dated 2024-12-31. The Arc Pro B390 lists a predecessor of HD Graphics-WM, while the Graphics 24EU Mobile has no predecessor listed.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The Intel Arc Pro B390 delivers 7.680 TFLOPS FP32, which is twenty times the 384.0 GFLOPS of the Intel Graphics 24EU Mobile.

Q: Does the Intel Graphics 24EU Mobile support ray tracing?

A: No. The database lists 12 RT cores for the Arc Pro B390 and no RT cores for the Graphics 24EU Mobile.

Q: What is the TDP difference between the two GPUs?

A: The Arc Pro B390 has an 80 W TDP, while the Graphics 24EU Mobile has a 6 W TDP.

Q: Do both GPUs use the same architecture?

A: No. The Arc Pro B390 uses Xe3-LPG on a 3 nm process, and the Graphics 24EU Mobile uses Xe-LP on a 10 nm process.

Q: Which GPU supports DirectX 12 Ultimate?

A: Only the Arc Pro B390 supports DirectX 12 Ultimate (12_2). The Graphics 24EU Mobile is limited to DirectX 12 (12_1).

Q: What are the boost clock speeds?

A: The Arc Pro B390 boosts to 2500 MHz, while the Graphics 24EU Mobile boosts to 1000 MHz. Both have a 300 MHz base clock.

Head-to-Head Benchmarks

The database contains no recorded benchmark scores for either the Intel Arc Pro B390 or the Intel Graphics 24EU Mobile. The head-to-head comparison must therefore be derived from the specification data, which the database does provide in full.

The largest win for the Arc Pro B390 is in FP32 compute. At 7.680 TFLOPS, it delivers exactly twenty times the 384.0 GFLOPS of the Graphics 24EU Mobile. This ratio holds for FP16 as well: 15.36 TFLOPS versus 768.0 GFLOPS, again a twenty-fold difference. For any shader-bound workload, the Arc Pro B390 has an overwhelming advantage.

Texture rate shows a ten-fold lead for the Arc Pro B390: 120.0 GTexel/s versus 12.00 GTexel/s. This comes from the combination of 48 TMUs at 2500 MHz versus 12 TMUs at 1000 MHz. Pixel rate is fifteen times higher on the Arc Pro B390: 60.00 GPixel/s versus 4.000 GPixel/s, driven by 24 ROPs versus 4 ROPs.

The shading unit count is eight times higher on the Arc Pro B390: 1536 versus 192. The RT core count is 12 versus zero. The boost clock is 2500 MHz versus 1000 MHz. Every compute-related specification in the database favors the Arc Pro B390 by a wide margin.

The Graphics 24EU Mobile does hold one clear advantage: power draw. The 6 W TDP is a fraction of the 80 W TDP of the Arc Pro B390. In a power-constrained environment, the Graphics 24EU Mobile can operate where the Arc Pro B390 cannot. The database also lists different bus interfaces, with the Graphics 24EU Mobile using Ring Bus and the Arc Pro B390 using IGP.

Both parts use System Shared memory with System Dependent bandwidth, so the memory bandwidth comparison is not fixed by the database. The process node difference (3 nm versus 10 nm) suggests the Arc Pro B390 has a manufacturing advantage, but the database does not list transistor counts or die sizes to quantify it.

The release dates place the Graphics 24EU Mobile earlier (2024-12-31) than the Arc Pro B390 (2026-01-26). The Arc Pro B390 has a predecessor (HD Graphics-WM), while the Graphics 24EU Mobile does not. Both are listed as Active production status.

In the absence of benchmark scores, the specification data provides a definitive ordering: the Arc Pro B390 is the higher-performance part by every compute metric, while the Graphics 24EU Mobile is the lower-power, simpler integration option. The percentile ranking for both is listed as 50 against all GPUs, but with no benchmark scores recorded, this percentile carries no comparative weight in the database.