Intel Arc B390 vs Intel Graphics 24EU Mobile Comparison

Intel
GPU

Intel Arc B390

CORE STATE Panther Lake
VRAM System Shared
CLOCK SPEED 2500 MHz
TDP 80 W
BUS WIDTH System Shared
ARCHITECTURE Xe3-LPG
nm
PROCESS 3 nm
LAUNCH DATE 2026
VS
Intel
GPU

Graphics 24EU Mobile

CORE STATE Twin Lake
VRAM System Shared
CLOCK SPEED 1000 MHz
TDP 6 W
BUS WIDTH System Shared
ARCHITECTURE Xe-LP
nm
PROCESS 10 nm
LAUNCH DATE 2025

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
1,482
N/A

Analysis: Intel Arc B390 vs Intel Graphics 24EU Mobile

FAQ

Q: How do the two Intel graphics solutions compare in raw benchmark scores?

A: The Intel Arc B390 has a recorded average benchmark score of 1482 in 3DMark Steel Nomad DX12, while the Intel Graphics 24EU Mobile has no recorded benchmark scores in the database, resulting in an average score of 0.

Q: What is the architectural generation difference between the two?

A: The Intel Arc B390 uses the Xe3-LPG architecture on the Panther Lake chip, part of the Arc Graphics-M (Panther Lake) generation. The Intel Graphics 24EU Mobile uses the Xe-LP architecture on the Twin Lake chip, part of the HD Graphics-T (Twin Lake) generation.

Q: Which GPU has a higher boost clock?

A: The Intel Arc B390 boosts to 2500 MHz, whereas the Intel Graphics 24EU Mobile boosts to 1000 MHz. Both share the same 300 MHz base clock.

Q: Do both GPUs support the same DirectX version?

A: No. The Intel Arc B390 supports DirectX 12 Ultimate (12_2), while the Intel Graphics 24EU Mobile supports DirectX 12 (12_1). Both support OpenGL 4.6 and Vulkan 1.4.

Q: How does the shading unit count differ?

A: The Intel Arc B390 packs 1536 shading units, while the Intel Graphics 24EU Mobile has 192 shading units, an eightfold difference in this specification.

Q: What is the TDP disparity between the two?

A: The Intel Arc B390 is rated at 80 W, while the Intel Graphics 24EU Mobile is rated at 6 W. The Arc B390 also has no power connectors, using an IGP slot width, while the 24EU Mobile uses a Ring Bus interface.

Architecture Differences

The Intel Arc B390 and Intel Graphics 24EU Mobile represent two distinct design philosophies from Intel, separated by architecture, process node, and target application. The Arc B390 is built on the Xe3-LPG architecture, which is the third-generation low-power graphics architecture in Intel's lineup, integrated into the Panther Lake chip. This places it in the Arc Graphics-M (Panther Lake) generation, a family designed for more demanding integrated graphics workloads. In contrast, the Intel Graphics 24EU Mobile uses the older Xe-LP architecture, the first-generation low-power design, found on the Twin Lake chip within the HD Graphics-T (Twin Lake) generation.

The process node difference is significant. The Arc B390 is fabricated on a 3 nm process, while the 24EU Mobile is fabricated on a 10 nm process. This manufacturing gap contributes to the substantial differences in transistor density and power efficiency, though exact transistor counts and die sizes are not recorded for either part. Both are manufactured by Intel, so the process shrink represents an internal generational leap rather than a foundry change.

Execution unit configuration forms the core of the architectural gap. The Arc B390 contains 1536 shading units, 48 texture mapping units, 24 render output units, and 12 ray tracing cores. The 24EU Mobile, as its name suggests, has far fewer resources: 192 shading units, 12 texture mapping units, and only 4 render output units. Critically, the 24EU Mobile has no ray tracing cores at all, making it unsuitable for hardware-accelerated ray tracing workloads. The Arc B390's 12 ray tracing cores are a defining feature of the newer architecture, enabling DirectX 12 Ultimate features that the older part cannot access.

Clock behavior also reflects the architectural intent. Both start at a 300 MHz base clock, but the Arc B390 boosts to 2500 MHz, a 2.5x higher boost ceiling than the 24EU Mobile's 1000 MHz. This boost capability, combined with the larger execution resource pool, explains the massive throughput difference. The Arc B390 achieves a pixel rate of 60.00 GPixel/s and a texture rate of 120.0 GTexel/s, versus 4.000 GPixel/s and 12.00 GTexel/s for the 24EU Mobile. Floating point performance scales similarly: the Arc B390 delivers 7.680 TFLOPS FP32 and 15.36 TFLOPS FP16 (2:1), while the 24EU Mobile delivers 384.0 GFLOPS FP32 and 768.0 GFLOPS FP16 (2:1). The Arc B390 is exactly 20 times higher in FP32 throughput.

API support differs at the DirectX level. The Arc B390 supports DirectX 12 Ultimate (12_2), which includes advanced features like variable rate shading and mesh shaders. The 24EU Mobile is limited to DirectX 12 (12_1), a lower feature level. Both support OpenGL 4.6 and Vulkan 1.4, so the gap is confined to Microsoft's graphics API. The production status for both is listed as Active, meaning both are currently available in the market.

Head-to-Head Benchmarks

The head-to-head benchmark comparison is one-sided due to data availability. The Intel Arc B390 has a single recorded benchmark result: a 3DMark Steel Nomad DX12 score of 1482. The Intel Graphics 24EU Mobile has no recorded benchmarks in the database, giving it an average benchmark score of 0. The head-to-head benchmark table is empty, and the win count shows zero wins for each side, reflecting the absence of direct comparative runs rather than tied performance.

The Arc B390's score of 1482 places it in the 9th percentile of all GPUs in the database. This percentile ranking means 91% of recorded GPUs score higher, which seems low at first glance. However, the nearest rivals provide context for what this score represents. The NVIDIA GeForce GT 520MX averages 1463, a delta of 1.3% behind the Arc B390. The NVIDIA GeForce 800M averages 1460, 1.5% behind. The NVIDIA GeForce GT 625 OEM averages 1446, 2.5% behind. The NVIDIA GeForce GT 710 averages 1443, 2.7% behind. The Arc B390 is ahead of all four recorded rivals, but the margins are narrow, ranging from 1.3% to 2.7%. This indicates that the Arc B390's raw performance in this specific test sits just above a cluster of older discrete entry-level GPUs.

The 24EU Mobile's lack of benchmark data means it cannot be positioned against any rivals. Its 50th percentile ranking is a default value based on no measurements, not a meaningful performance indicator. The absence of nearest rivals confirms that the database has no comparative data for this part. In practical terms, the Arc B390's recorded score is the only quantitative performance evidence available, and it outperforms the 24EU Mobile by the simple fact that the latter has no score at all.

The performance gap implied by the specifications is stark. The Arc B390's 7.680 TFLOPS FP32 is exactly 20 times the 24EU Mobile's 384.0 GFLOPS. The pixel rate difference is 15 times (60.00 vs 4.000 GPixel/s), and the texture rate difference is 10 times (120.0 vs 12.00 GTexel/s). These ratios, combined with the 2.5x boost clock advantage, paint a picture of a GPU designed for substantially heavier workloads. The data shows that the Arc B390 is not just faster, it is in a different performance class entirely, even if its absolute benchmark score places it low in the global GPU ranking.

Specification Differences

The specification tables reveal every major difference between the two parts. The chip designations differ: Panther Lake for the Arc B390 versus Twin Lake for the 24EU Mobile. The architectures are Xe3-LPG versus Xe-LP. The generation names are Arc Graphics-M (Panther Lake) versus HD Graphics-T (Twin Lake). The process node is 3 nm versus 10 nm, a significant manufacturing advantage for the newer part.

Clock speeds diverge sharply. Both have a 300 MHz base clock, but the boost clock is 2500 MHz for the Arc B390 and 1000 MHz for the 24EU Mobile. Memory configuration is identical in structure: both use System Shared memory with System Shared bus width and System Dependent bandwidth. The memory size and type are also System Shared for both, meaning neither has dedicated VRAM.

The execution unit counts are the most dramatic differentiators. Shading units: 1536 versus 192. Texture mapping units: 48 versus 12. Render output units: 24 versus 4. Ray tracing cores: 12 versus none. The Arc B390 has no tensor cores recorded, and neither does the 24EU Mobile. Pixel rate is 60.00 GPixel/s versus 4.000 GPixel/s. Texture rate is 120.0 GTexel/s versus 12.00 GTexel/s. FP32 compute is 7.680 TFLOPS versus 384.0 GFLOPS. FP16 compute is 15.36 TFLOPS versus 768.0 GFLOPS, both using 2:1 ratio.

Power consumption differs by an order of magnitude: 80 W TDP for the Arc B390 versus 6 W for the 24EU Mobile. The Arc B390 lists power connectors as None, while the 24EU Mobile does not list a power connector field value. Both use IGP slot width, meaning neither is a discrete card. The bus interface differs: IGP for the Arc B390 versus Ring Bus for the 24EU Mobile. Display outputs are Portable Device Dependent for both, indicating they are designed for mobile or integrated deployments.

API support shows a DirectX feature level gap: 12 Ultimate (12_2) for the Arc B390 versus 12 (12_1) for the 24EU Mobile. OpenGL 4.6 and Vulkan 1.4 are identical across both. Dimensions are unrecorded for both parts. Production status is Active for both. Release dates differ: 2026-01-26 for the Arc B390 and 2024-12-31 for the 24EU Mobile. Neither has a launch MSRP, predecessor, or successor listed. The 24EU Mobile has no power connector data, while the Arc B390 explicitly lists None.

Where Each One Wins

The Intel Arc B390 wins in every recorded performance metric. Its 3DMark Steel Nomad DX12 score of 1482 is the only quantitative benchmark available. The 24EU Mobile has no benchmark scores, so it cannot claim a single recorded performance win. The Arc B390 also wins on architectural features: it has ray tracing cores, the 24EU Mobile does not. It supports DirectX 12 Ultimate, the 24EU Mobile only reaches DirectX 12 (12_1). It has a higher boost clock, more shading units, more texture mapping units, more render output units, and higher pixel, texture, and compute rates across the board.

The 24EU Mobile wins in power efficiency. Its 6 W TDP is 13.3 times lower than the Arc B390's 80 W. For thermally constrained or battery-powered devices, this power envelope is the decisive factor. The 24EU Mobile also uses the older 10 nm process, which, while less advanced, may be cheaper to integrate into low-power Twin Lake systems. The Ring Bus interface suggests a different integration approach compared to the Arc B390's IGP bus.

For use cases, the Arc B390 is positioned for workloads that need graphics throughput: light gaming, media creation, or any application that benefits from 7.680 TFLOPS FP32 and 12 ray tracing cores. The 24EU Mobile is positioned for basic display output, video playback, and low-intensity graphical interfaces where 384.0 GFLOPS is sufficient and 6 W is the budget. The Arc B390's 12_2 DirectX support enables modern game features, while the 24EU Mobile's 12_1 support is adequate for older or less demanding titles.

The nearest rivals for the Arc B390 all sit within 2.7% of its score, meaning it edges out several older NVIDIA discrete parts. The GT 520MX, GeForce 800M, GT 625 OEM, and GT 710 are all beaten by the Arc B390. This suggests the Arc B390 competes with entry-level discrete GPUs from a previous era, despite being an integrated part. The 24EU Mobile has no rivals in the database, so no comparative positioning is possible.

The Verdict

The data indicates a clear performance hierarchy: the Intel Arc B390 is a substantially more capable graphics processor than the Intel Graphics 24EU Mobile. The Arc B390 delivers 7.680 TFLOPS FP32, 60.00 GPixel/s pixel rate, and 120.0 GTexel/s texture rate, all of which are multiples of the 24EU Mobile's figures. It has 12 ray tracing cores where the 24EU Mobile has none, and it supports DirectX 12 Ultimate where the 24EU Mobile is limited to DirectX 12 (12_1). Its recorded 3DMark Steel Nomad score of 1482 places it ahead of four NVIDIA rivals by margins of 1.3% to 2.7%, confirming that its raw performance is measurable and competitive within its class.

The Intel Graphics 24EU Mobile wins on power. Its 6 W TDP versus the Arc B390's 80 W makes it suitable for ultra-low-power devices where every watt matters. The 10 nm process and older Xe-LP architecture are sufficient for basic graphics duties, and the absence of benchmark scores does not mean the part is non-functional, it simply means the database has no recorded measurements for it. Its 50th percentile ranking is a placeholder, not a performance verdict.

The choice between the two depends entirely on the power envelope and workload requirements. For any application that demands graphics compute, ray tracing, or modern DirectX features, the Intel Arc B390 is the only option with recorded evidence of capability. For passive or fanless designs, battery-critical portables, or systems where 6 W is the maximum available power, the Intel Graphics 24EU Mobile is the appropriate fit. The Arc B390's 20x FP32 advantage and 15x pixel rate advantage are not marginal differences; they represent different product categories. The database records no scenario where the 24EU Mobile outperforms the Arc B390 in raw graphics throughput.

The release dates align with the architectural progression: the 24EU Mobile debuted in 2024-12-31 on the older Xe-LP architecture, and the Arc B390 followed on 2026-01-26 with Xe3-LPG. Both are Active in production, so neither is a legacy or discontinued part. The Arc B390's 80 W TDP and IGP form factor suggest it targets thin-and-light laptops with higher thermal budgets, while the 24EU Mobile's 6 W TDP and Ring Bus interface target the most power-constrained segments. The verdict from the data is unambiguous: the Intel Arc B390 is the superior graphics processor, and the Intel Graphics 24EU Mobile is the superior power-saving option.

DETAILED SPECIFICATIONS

SPECIFICATION
B390
Graphics 24EU Mobile
Core Specs
Shading Units
1,536
192 -87.5%
Shaders
1,536
192 -87.5%
TMUs
48
12 -75.0%
ROPs
24
4 -83.3%
Execution Units
12
24 +100.0%
Clocks
Base Clock
300 MHz
300 MHz
Boost Clock
2500 MHz
1000 MHz
Memory Clock
System Shared
System Shared
Memory
Memory Size
System Shared
System Shared
Memory Type
System Shared
System Shared
Memory Bus
System Shared
System Shared
Bandwidth
System Dependent
System Dependent
Cache
L1 Cache
64 KB (per EU)
L2 Cache
16 MB
Performance
Pixel Rate
60.00 GPixel/s
4.000 GPixel/s
Texture Rate
120.0 GTexel/s
12.00 GTexel/s
FP32 (TFLOPS)
7.680 TFLOPS
384.0 GFLOPS
FP64 (TFLOPS)
960.0 GFLOPS (1:8)
FP16 (TFLOPS)
15.36 TFLOPS (2:1)
768.0 GFLOPS (2:1)
AI/RT
RT Cores
12
XMX Cores
96
Power
TDP
80 W
6 W
TDP (W)
80
6 -92.5%
Power Connectors
None
Architecture
Architecture
Xe3-LPG
Xe-LP
GPU Name
Panther Lake
Twin Lake
Generation
Arc Graphics-M (Panther Lake)
HD Graphics-T (Twin Lake)
Process Size
3 nm
10 nm
Transistors
unknown
unknown
Die Size
unknown
unknown
Foundry
Intel
Intel
API Support
DirectX
12 Ultimate (12_2)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
Shader Model
6.9
6.6
Physical
Slot Width
IGP
IGP
Outputs
Portable Device Dependent
Portable Device Dependent
Bus Interface
IGP
Ring Bus
Other
Production
Active
Active
View Arc B390 Details View Graphics 24EU Mobile Details