Intel Arc B390 vs Intel Arc Graphics 48EU Mobile Comparison

Head-to-Head Benchmarks

The benchmark data shows a single recorded measurement for the Intel Arc B390, and no recorded measurements for the Intel Arc Graphics 48EU Mobile. In the 3DMark Steel Nomad DX12 test, the Arc B390 scores 1482 points. This places it in the 9th percentile of all GPUs in the database. The Arc Graphics 48EU Mobile has no benchmark scores recorded, so a direct comparison of measured performance cannot be made.

The Arc B390’s nearest rivals in the database are all NVIDIA discrete mobile and OEM parts. It leads the GeForce GT 520MX by 1.3 percent, with that rival scoring 1463. The lead over the GeForce 800M is 1.5 percent, as that card scores 1460. The margin expands to 2.5 percent against the GeForce GT 625 OEM, which scores 1446, and to 2.7 percent against the GeForce GT 710, which scores 1443. These are narrow margins, indicating that the Arc B390 sits at the very low end of the performance spectrum despite being a modern integrated part.

The Arc Graphics 48EU Mobile has no rivals listed and no average benchmark score. Its percentile ranking of 50 is a default position in the database, not a reflection of measured performance. With no scores recorded, the data set provides no direct head-to-head result between these two Intel parts.

Where Each One Wins

The Arc B390 wins in every category where data exists. Its FP32 compute of 7.680 TFLOPS is substantially higher than the 1,382.4 GFLOPS of the Arc Graphics 48EU Mobile. That is a 5.6 times advantage in raw shader throughput, stemming from 1536 shading units versus 384. Texture rate follows the same pattern: the B390 delivers 120.0 GTexel/s against 43.20 GTexel/s, a 2.8 times difference. Pixel rate shows a 60.00 GPixel/s versus 14.40 GPixel/s comparison, a 4.2 times gap.

The B390 also carries 12 ray tracing cores, while the 48EU Mobile lists none. This gives the B390 a feature advantage in any workload that uses DirectX Raytracing or Vulkan ray tracing. The B390’s boost clock of 2500 MHz versus 1800 MHz on the 48EU Mobile contributes to its throughput advantage, though the core count difference is the dominant factor.

The 48EU Mobile wins in power efficiency. Its 28 W TDP is less than a third of the B390’s 80 W TDP. The 48EU Mobile also uses a Ring Bus interface, which is typical for integrated graphics in mobile system-on-chip designs, whereas the B390 also uses an IGP slot width but does not specify its bus interface beyond that. The 48EU Mobile’s lower power envelope makes it suitable for thin and light portable devices, while the B390’s higher power budget suggests a larger or more performance-oriented chassis.

Architecture Differences

The two GPUs come from different Intel process nodes and architectures. The Arc B390 uses the Panther Lake chip with the Xe3-LPG architecture, fabricated on a 3 nm process at Intel. The Arc Graphics 48EU Mobile uses the Meteor Lake chip with the Xe-LPG architecture, fabricated on a 10 nm process at Intel. The B390 represents a newer generation, released on 2026-01-26, while the 48EU Mobile launched earlier on 2023-12-13. The B390 belongs to the Arc Graphics-M (Panther Lake) generation, and the 48EU Mobile belongs to the Arc Graphics-M (Meteor Lake) generation.

The B390 has 1536 shading units, 48 texture mapping units, and 24 raster output units. The 48EU Mobile has 384 shading units, 24 TMUs, and 8 ROPs. The B390 includes 12 ray tracing cores; the 48EU Mobile does not list any. Both use system shared memory with system dependent bandwidth, so memory size, type, and bus width are identical in specification terms.

API support differs. The B390 supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The 48EU Mobile supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The DirectX feature level difference means the B390 can expose ray tracing and mesh shaders at the API level, while the 48EU Mobile is limited to the older 12_1 feature set.

The B390’s process node advantage is significant. A 3 nm process versus 10 nm allows for denser transistor packing and lower power per transistor, though the B390 still consumes more total power due to its larger shader array. The B390 also has a higher boost clock, 2500 MHz versus 1800 MHz, which further widens the compute gap.

The 48EU Mobile has a predecessor listed as HD Graphics-M, indicating it is part of Intel’s integrated graphics lineage for mobile processors. The B390 has no predecessor listed. The 48EU Mobile’s production status is Active, as is the B390’s.

The Verdict

The data shows a clear performance hierarchy. The Intel Arc B390 outperforms the Intel Arc Graphics 48EU Mobile by a wide margin in every measured or specified compute metric. The B390’s FP32 throughput is 5.6 times higher, its texture rate is 2.8 times higher, and its pixel rate is 4.2 times higher. It also offers ray tracing hardware and a newer DirectX feature level. Any workload that stresses shader throughput, texturing, or rasterization will favor the B390.

The Arc Graphics 48EU Mobile is not without merit. Its 28 W TDP makes it a low-power option for portable devices where battery life and thermal limits take priority over raw performance. Its Ring Bus interface and integrated design fit the Meteor Lake mobile platform. For basic display output, media playback, and light 2D workloads, the 48EU Mobile is sufficient.

The B390’s 80 W TDP is high for an integrated part. The database classifies it as IGP, meaning it is not a discrete card, but its power draw approaches low-end discrete GPU territory. This suggests the B390 is intended for larger laptops or all-in-one systems that can dissipate more heat.

The nearest rival data reinforces the B390’s position. It trades blows with decade-old NVIDIA discrete GPUs, leading them by margins of 1.3 to 2.7 percent. The B390 is not a high-performance part by any measure; it sits near the bottom of the database’s performance distribution. The 48EU Mobile has no comparable data, so its performance cannot be positioned against any rivals.

For users who need the maximum compute capability from an integrated GPU, the B390 is the only choice between these two. For users who prioritize low power consumption and have modest graphics needs, the 48EU Mobile is the more sensible option. The database does not contain any benchmark scores for the 48EU Mobile, so its actual performance remains unverified.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The Intel Arc B390 delivers 7.680 TFLOPS, while the Intel Arc Graphics 48EU Mobile delivers 1,382.4 GFLOPS. The B390 is approximately 5.6 times faster in raw shader throughput.

Q: Do both GPUs support ray tracing?

A: No. The Arc B390 includes 12 ray tracing cores. The Arc Graphics 48EU Mobile does not list any ray tracing cores.

Q: What is the power consumption difference?

A: The Arc B390 has a TDP of 80 W, while the Arc Graphics 48EU Mobile has a TDP of 28 W. The 48EU Mobile consumes less than half the power of the B390.

Q: Which GPU supports a higher DirectX feature level?

A: The Arc B390 supports DirectX 12 Ultimate (12_2). The Arc Graphics 48EU Mobile supports DirectX 12 (12_1). The B390’s feature level enables ray tracing and mesh shaders at the API level.

Q: How does the Arc B390 compare to its nearest rivals in the database?

A: The Arc B390 leads the NVIDIA GeForce GT 520MX by 1.3 percent, the GeForce 800M by 1.5 percent, the GeForce GT 625 OEM by 2.5 percent, and the GeForce GT 710 by 2.7 percent in the 3DMark Steel Nomad DX12 test.

Q: What are the process node differences?

A: The Arc B390 uses a 3 nm process at Intel. The Arc Graphics 48EU Mobile uses a 10 nm process at Intel. The B390’s process is newer and allows for higher clock speeds and greater transistor density.

Specification Differences

| Specification | Intel Arc B390 | Intel Arc Graphics 48EU Mobile |

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

| Chip | Panther Lake | Meteor Lake |

| Architecture | Xe3-LPG | Xe-LPG |

| Process Node | 3 nm | 10 nm |

| Generation | Arc Graphics-M (Panther Lake) | Arc Graphics-M (Meteor Lake) |

| Release Date | 2026-01-26 | 2023-12-13 |

| Base Clock | 300 MHz | 300 MHz |

| Boost Clock | 2500 MHz | 1800 MHz |

| Shading Units | 1536 | 384 |

| Texture Mapping Units | 48 | 24 |

| Raster Output Units | 24 | 8 |

| Ray Tracing Cores | 12 | None |

| Pixel Rate | 60.00 GPixel/s | 14.40 GPixel/s |

| Texture Rate | 120.0 GTexel/s | 43.20 GTexel/s |

| FP32 Performance | 7.680 TFLOPS | 1,382.4 GFLOPS |

| FP16 Performance | 15.36 TFLOPS (2:1) | 2.765 TFLOPS (2:1) |

| TDP | 80 W | 28 W |

| Bus Interface | IGP | Ring Bus |

| DirectX Support | 12 Ultimate (12_2) | 12 (12_1) |

| Predecessor | None | HD Graphics-M |