Intel Arc Graphics 48EU Mobile vs Intel Arc Pro B390 Comparison

Head-to-Head Benchmarks

The database contains no recorded benchmark scores for either the Intel Arc Graphics 48EU Mobile or the Intel Arc Pro B390. The head-to-head benchmark table is empty, with zero wins recorded for each part. This absence of empirical data means any performance comparison must be derived from the architectural and specification differences recorded in the database, rather than from direct measurement results.

The Intel Arc Graphics 48EU Mobile carries a 50th percentile ranking versus all GPUs, and the Intel Arc Pro B390 also sits at the 50th percentile. Both parts occupy the same percentile position, which indicates that the database has not yet placed either one above the other in the overall performance distribution. The average benchmark score for both is recorded as zero, further confirming that no test results have been logged.

Without benchmark deltas, the raw compute figures provide the only measurable comparison. The Arc Pro B390 delivers 7.680 TFLOPS of FP32 throughput, while the Arc Graphics 48EU Mobile delivers 1,382.4 GFLOPS, which converts to approximately 1.382 TFLOPS. The B390 therefore offers roughly 5.5 times the FP32 throughput of the 48EU part, a substantial gap that would translate into large performance differences in shader-bound workloads. In FP16, the B390 records 15.36 TFLOPS versus 2.765 TFLOPS for the 48EU, again a roughly 5.5 times advantage.

Pixel throughput tells a similar story. The B390 reaches 60.00 GPixel/s, while the 48EU part manages 14.40 GPixel/s. Texture rate follows the same pattern: 120.0 GTexel/s for the B390 versus 43.20 GTexel/s for the 48EU. These figures indicate that the B390 should dominate in fill-rate-limited scenarios such as high-resolution rendering and heavy texture sampling.

Where Each One Wins

The Intel Arc Graphics 48EU Mobile operates with a 28 W TDP, which is the lower power envelope of the two. This makes it the more appropriate choice for constrained mobile platforms where thermal and power budgets are tight. Its 300 MHz base clock and 1800 MHz boost clock are both lower than the B390's 300 MHz base and 2500 MHz boost, but the reduced power draw allows it to fit into thinner and lighter portable designs. The 48EU part also uses the Xe-LPG architecture built on Intel's 10 nm process, which is an older node but one that is proven in the Meteor Lake generation.

The Intel Arc Pro B390 is the clear winner in raw capability. Its 1536 shading units dwarf the 48EU's 384, and it carries 48 texture mapping units versus 24, plus 24 ROPs versus 8. The B390 also includes 12 ray tracing cores, a feature entirely absent from the 48EU part. This makes the B390 the only one of the two that can handle hardware-accelerated ray tracing workloads. Its 80 W TDP reflects the higher performance ceiling, and its 3 nm process node from Intel represents a significant manufacturing advancement over the 10 nm node used by the 48EU.

The B390 supports DirectX 12 Ultimate (12_2), while the 48EU part supports DirectX 12 (12_1). This means the B390 is aligned with the latest graphics feature level, including features tied to DirectX 12 Ultimate, whereas the 48EU part predates that specification level. Both support OpenGL 4.6 and Vulkan 1.4, so in those API environments the two are on equal footing.

The 48EU part belongs to the Arc Graphics-M (Meteor Lake) generation and is built on the Xe-LPG architecture. The B390 belongs to the Arc Graphics-WM (Panther Lake) generation and uses the newer Xe3-LPG architecture. The architectural leap from Xe-LPG to Xe3-LPG, combined with the process shrink from 10 nm to 3 nm, explains much of the performance gap between the two.

The Verdict

The data clearly separates these two parts into different performance classes. The Intel Arc Pro B390 is the stronger GPU by every measured compute metric in the database. Its FP32 throughput of 7.680 TFLOPS, FP16 throughput of 15.36 TFLOPS, pixel rate of 60.00 GPixel/s, and texture rate of 120.0 GTexel/s place it far above the Intel Arc Graphics 48EU Mobile, which records 1,382.4 GFLOPS, 2.765 TFLOPS, 14.40 GPixel/s, and 43.20 GTexel/s respectively. The B390 also has four times the shading units, double the TMUs, triple the ROPs, and a dedicated set of 12 ray tracing cores.

The 48EU Mobile does have one clear advantage: power consumption. At 28 W versus 80 W, it draws less than half the power of the B390. For a mobile integrated GPU, that power efficiency is critical. The 48EU part is designed for portable devices where battery life and thermal limits take priority over maximum frame rates. Its 300 MHz base clock and 1800 MHz boost clock are sufficient for light graphics work, and the system-shared memory architecture keeps the design simple.

The B390 is the choice for workloads that demand graphics throughput. Its higher boost clock of 2500 MHz, larger shader array, and ray tracing support make it suitable for more demanding rendering tasks. The 3 nm process node indicates a much newer and denser implementation, and the DirectX 12 Ultimate support means it can run the most modern graphics feature sets.

Users who need maximum graphics capability from an Intel integrated solution should select the Arc Pro B390. Users who need a low-power integrated GPU for a portable device should select the Arc Graphics 48EU Mobile. The database does not yet contain benchmark results to confirm real-world deltas, but the specification gap is wide enough that the performance hierarchy is not in doubt.

FAQ

Q: Which GPU has higher FP32 performance?

A: The Intel Arc Pro B390 delivers 7.680 TFLOPS of FP32 throughput, compared to 1,382.4 GFLOPS for the Intel Arc Graphics 48EU Mobile.

Q: Does either GPU support ray tracing?

A: Only the Intel Arc Pro B390 includes ray tracing cores, with 12 RT cores recorded. The Intel Arc Graphics 48EU Mobile has no RT cores listed in the database.

Q: What is the TDP difference between the two?

A: The Intel Arc Graphics 48EU Mobile has a 28 W TDP, while the Intel Arc Pro B390 has an 80 W TDP.

Q: Which part supports DirectX 12 Ultimate?

A: The Intel Arc Pro B390 supports DirectX 12 Ultimate (12_2). The Intel Arc Graphics 48EU Mobile supports DirectX 12 (12_1), which is a lower feature level.

Q: What are the boost clocks of each GPU?

A: The Intel Arc Graphics 48EU Mobile boosts to 1800 MHz. The Intel Arc Pro B390 boosts to 2500 MHz. Both have a 300 MHz base clock.

Q: How do the shading unit counts compare?

A: The Intel Arc Pro B390 has 1536 shading units. The Intel Arc Graphics 48EU Mobile has 384 shading units.

Architecture Differences

The two GPUs come from different architecture generations. The Intel Arc Graphics 48EU Mobile uses the Xe-LPG architecture, built on Intel's 10 nm process node. It is part of the Arc Graphics-M (Meteor Lake) generation. The Intel Arc Pro B390 uses the Xe3-LPG architecture, built on Intel's 3 nm process node, and belongs to the Arc Graphics-WM (Panther Lake) generation. The process node difference from 10 nm to 3 nm represents a major manufacturing advancement, allowing the B390 to pack far more compute resources into a similar integrated form factor.

The B390's Xe3-LPG architecture includes 12 ray tracing cores, a feature that the Xe-LPG based 48EU part does not have at all. The B390 also supports DirectX 12 Ultimate (12_2), while the 48EU part only reaches DirectX 12 (12_1). Both GPUs support OpenGL 4.6 and Vulkan 1.4, so in those APIs the feature sets match. The B390 uses an IGP bus interface, while the 48EU part uses a Ring Bus interface. The B390 has no power connectors listed, which is consistent with an integrated part, and the 48EU part also has no power connectors recorded.

The memory architecture is identical in structure: both use system-shared memory with system-shared type, bus width, and system-dependent bandwidth. Neither GPU has a dedicated VRAM pool, so both rely on the host system's memory. The display outputs are listed as portable device dependent for both, meaning the actual output configuration varies by the laptop or mobile platform in which they are installed.

Specification Differences

The Intel Arc Pro B390 leads in nearly every compute specification. Its shading unit count is 1536 versus 384 for the 48EU Mobile, a 4x difference. Texture mapping units are 48 versus 24, and ROPs are 24 versus 8. The B390 has 12 ray tracing cores; the 48EU has none. FP32 throughput is 7.680 TFLOPS versus 1,382.4 GFLOPS. FP16 throughput is 15.36 TFLOPS versus 2.765 TFLOPS. Pixel rate is 60.00 GPixel/s versus 14.40 GPixel/s. Texture rate is 120.0 GTexel/s versus 43.20 GTexel/s.

The boost clocks differ substantially: 2500 MHz for the B390 versus 1800 MHz for the 48EU, while both share a 300 MHz base clock. The TDP is 80 W for the B390 and 28 W for the 48EU. The process node is 3 nm for the B390 and 10 nm for the 48EU. The bus interface is IGP for the B390 and Ring Bus for the 48EU.

The architectures differ: Xe3-LPG for the B390 and Xe-LPG for the 48EU. The generations differ as well: Arc Graphics-WM (Panther Lake) versus Arc Graphics-M (Meteor Lake). The B390 records a DirectX support level of 12 Ultimate (12_2), while the 48EU records 12 (12_1). OpenGL and Vulkan support are identical at 4.6 and 1.4 respectively.

The B390 lists its power connectors as "None", while the 48EU has no power connector field recorded. The B390's transistor count and die size are listed as "unknown", and the 48EU has no transistor count or die size data. Neither part has a recorded launch MSRP in the database. The B390 was released on 2026-01-26, while the 48EU was released on 2023-12-13. The 48EU's predecessor is HD Graphics-M, and the B390's predecessor is HD Graphics-WM. Neither part has a recorded successor. Both are marked as Active in production status.