Intel Arc Graphics 2 Xe Mobile vs Intel Arc Graphics 64EU Comparison

Intel
GPU

Intel Arc Graphics 2 Xe Mobile

CORE STATE Wildcat Lake
VRAM System Shared
CLOCK SPEED 2500 MHz
TDP 25 W
BUS WIDTH System Shared
ARCHITECTURE Xe3-LPG
nm
PROCESS 3 nm
LAUNCH DATE 2026
VS
Intel
GPU

Arc Graphics 64EU

CORE STATE Arrow Lake-S
VRAM System Shared
CLOCK SPEED 1900 MHz
TDP 65 W
BUS WIDTH System Shared
ARCHITECTURE Xe-LPG
nm
PROCESS 3 nm
LAUNCH DATE 2024

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
N/A
733

Analysis: Intel Arc Graphics 2 Xe Mobile vs Intel Arc Graphics 64EU

Intel Arc Graphics 2 Xe Mobile and Intel Arc Graphics 64EU represent two distinct approaches to integrated graphics within Intel’s current lineup. The data shows a clear split: the 64EU part delivers substantially higher raw throughput, while the 2 Xe Mobile part operates at a much lower power envelope and uses a newer architecture. Benchmark results are sparse for the 2 Xe Mobile, which has no recorded scores, while the 64EU holds a single 3DMark Steel Nomad DX12 score of 733. The 64EU also carries a percentile ranking of 3 against all GPUs, placing it in the lower performance tier, with direct rivals that include Intel Arc Graphics 32EU and 24EU, both scoring 733 with a 0 percent delta, the AMD Radeon HD 6470M at 723 with a 1.4 percent delta, and the NVIDIA GeForce GT 415M at 751 with a negative 2.4 percent delta.

Where Each One Wins

The Intel Arc Graphics 64EU wins decisively on raw compute and fill rates. Its FP32 throughput is 1.946 TFLOPS, which is 52 percent higher than the 1,280.0 GFLOPS (1.280 TFLOPS) of the 2 Xe Mobile. Pixel rate is 30.40 GPixel/s versus 20.00 GPixel/s, a 52 percent advantage. Texture rate is 60.80 GTexel/s versus 40.00 GTexel/s, also a 52 percent advantage. The 64EU doubles the shading units (512 versus 256), TMUs (32 versus 16), and ROPs (16 versus 8). In any workload that scales with shader count or memory throughput, the 64EU has the clear edge. The recorded 3DMark Steel Nomad DX12 score of 733 confirms this, though there is no comparable score for the 2 Xe Mobile.

The 2 Xe Mobile wins on efficiency and architectural generation. It uses a 25 W TDP, which is 40 watts lower than the 65 W TDP of the 64EU. That power difference is substantial for integrated graphics, as it directly affects thermal headroom, chassis design, and battery life in portable systems. The 2 Xe Mobile also boosts to 2500 MHz, which is 600 MHz higher than the 1900 MHz boost of the 64EU. The higher clock partially compensates for the smaller execution resource pool, but not enough to overcome the 64EU’s doubling of cores. The 2 Xe Mobile belongs to the Arc Graphics-M (Wildcat Lake) generation and uses the Xe3-LPG architecture, whereas the 64EU uses the older Xe-LPG architecture from the Arc Graphics (Arrow Lake) generation. The Xe3-LPG architecture is the newer design in this comparison.

The 64EU includes 2 ray tracing cores in its specification list, while the 2 Xe Mobile has no RT cores listed. This gives the 64EU a feature advantage for DirectX Raytracing workloads, though the database does not record any specific ray tracing benchmark for either part. The 64EU also reports a transistor count of 17,800 million and a die size of 243 mm², with a transistor density of 73.3M per mm², all fabricated by TSMC. The 2 Xe Mobile is fabricated by Intel on a 3 nm process, but its transistor count, die size, and density are listed as unknown. The 64EU is the only part in this comparison with a measured benchmark result, so all performance conclusions derive from that single score and the theoretical throughput figures.

Architecture Differences

The two integrated GPUs diverge at the architecture level. The 2 Xe Mobile uses Xe3-LPG, which is the third-generation low-power graphics architecture from Intel, built on a 3 nm node at Intel’s own foundry. The 64EU uses Xe-LPG, the previous generation low-power graphics architecture, also built on a 3 nm node but at TSMC. The foundry difference is a key manufacturing distinction, though the database does not provide comparative yield or efficiency data. The 2 Xe Mobile’s chip is Wildcat Lake, while the 64EU’s chip is Arrow Lake-S, indicating different target platforms: the former for mobile, the latter for desktop or larger mobile processors.

Compute resources differ sharply. The 2 Xe Mobile has 256 shading units, 16 TMUs, 8 ROPs, and 2 RT cores. The 64EU has 512 shading units, 32 TMUs, 16 ROPs, and no RT cores listed. The absence of RT cores on the 64EU creates an odd inversion: the larger GPU lacks a feature that the smaller one has. Both parts report DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4 support. Memory is system shared for both, with system dependent bandwidth, so neither part has dedicated VRAM. The 64EU’s compute rates are about 52 percent higher across the board, which aligns with the doubled execution units.

Clock behavior differs. The 2 Xe Mobile has a 300 MHz base and 2500 MHz boost. The 64EU has a 300 MHz base and 1900 MHz boost. The higher boost on the 2 Xe Mobile reflects the lower power target and the newer architecture’s ability to scale frequency. Pixel rate for the 2 Xe Mobile is 20.00 GPixel/s, derived from its 8 ROPs and boost clock, while the 64EU achieves 30.40 GPixel/s from 16 ROPs at a lower clock. Texture rate follows the same pattern: 40.00 GTexel/s versus 60.80 GTexel/s. The FP16 figures are 2.560 TFLOPS for the 2 Xe Mobile and 3.891 TFLOPS for the 64EU, both at a 2:1 ratio relative to FP32.

The bus interface differs: the 2 Xe Mobile uses an IGP interface, while the 64EU uses a Ring Bus. Display outputs are also platform dependent, with the 2 Xe Mobile depending on the portable device and the 64EU depending on the motherboard. The 64EU lists a TDP of 65 W, which is high for integrated graphics and suggests it may be paired with a powerful desktop processor. The 2 Xe Mobile’s 25 W TDP fits a low-power mobile design. Neither part has a launch MSRP listed in the database.

The Verdict

The benchmark data indicates that the Intel Arc Graphics 64EU is the faster GPU in absolute terms. Its FP32 throughput of 1.946 TFLOPS, pixel rate of 30.40 GPixel/s, and texture rate of 60.80 GTexel/s all exceed the corresponding figures for the 2 Xe Mobile by roughly 52 percent. The 64EU also has a recorded 3DMark Steel Nomad DX12 score of 733, which places it in the 3rd percentile of all GPUs. Direct rivals in the database include the Intel Arc Graphics 32EU and 24EU, both with identical average scores of 733, the AMD Radeon HD 6470M at 723, which trails by 1.4 percent, and the NVIDIA GeForce GT 415M at 751, which leads by 2.4 percent. The 64EU sits in a narrow band around those older discrete parts, meaning its performance is comparable to early-2010s entry-level discrete GPUs.

The 2 Xe Mobile has no recorded benchmarks and no nearest rivals in the database. Its percentile ranking is 50, which is a placeholder value given the absence of data. The theoretical figures show it is a smaller GPU, with 256 shading units and 1,280.0 GFLOPS, but it also runs at a much lower 25 W TDP. For systems where power consumption is the primary constraint, the 2 Xe Mobile is the better fit. For systems where peak graphics performance matters more, the 64EU is the better fit. The 64EU’s 65 W TDP is 2.6 times higher than the 2 Xe Mobile’s 25 W, so any performance advantage comes with a significant power cost.

The newer Xe3-LPG architecture of the 2 Xe Mobile does not translate into a measured performance win, since no benchmark score exists. The architecture does bring a higher boost clock of 2500 MHz versus 1900 MHz, and the 2 Xe Mobile includes 2 RT cores while the 64EU lists none. The 64EU compensates with double the shading units, TMUs, and ROPs, plus a higher FP32 ceiling. The data suggests that the 64EU is the choice for compute-heavy or rasterization-heavy tasks, while the 2 Xe Mobile is the choice for power-limited mobile platforms that still want the latest architecture and hardware ray tracing support.

FAQ

Q: Which GPU has higher FP32 performance?

A: The Intel Arc Graphics 64EU has 1.946 TFLOPS of FP32 throughput, which is about 52 percent higher than the 1,280.0 GFLOPS of the Intel Arc Graphics 2 Xe Mobile.

Q: Does the Intel Arc Graphics 2 Xe Mobile have any benchmark results?

A: No. The database records zero benchmarks for the 2 Xe Mobile, with an average benchmark score of 0 and a percentile of 50. The 64EU has one recorded 3DMark Steel Nomad DX12 score of 733.

Q: How does the Intel Arc Graphics 64EU compare to its nearest rivals?

A: The 64EU scores 733 in 3DMark Steel Nomad DX12, matching the Intel Arc Graphics 32EU and 24EU exactly with a 0 percent delta. It is 1.4 percent ahead of the AMD Radeon HD 6470M, which scores 723, and 2.4 percent behind the NVIDIA GeForce GT 415M, which scores 751.

Q: What are the power requirements of each GPU?

A: The Intel Arc Graphics 2 Xe Mobile has a TDP of 25 W, while the Intel Arc Graphics 64EU has a TDP of 65 W. The 64EU consumes 40 W more at its rated TDP.

Q: Do both GPUs support the same graphics APIs?

A: Yes. Both report DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4 support.

Q: Which GPU has more shading units?

A: The Intel Arc Graphics 64EU has 512 shading units, double the 256 shading units of the Intel Arc Graphics 2 Xe Mobile. The 64EU also has 32 TMUs and 16 ROPs, versus 16 TMUs and 8 ROPs on the 2 Xe Mobile.

Head-to-Head Benchmarks

The only recorded benchmark in this comparison is the 3DMark Steel Nomad DX12 test for the Intel Arc Graphics 64EU, which scored 733. There is no corresponding score for the 2 Xe Mobile, so a direct head-to-head benchmark result is unavailable. The database shows 0 wins for each part in head-to-head tests. The performance gap must be inferred from the theoretical specifications.

The largest single-specification win for the 64EU is in FP32 compute: 1.946 TFLOPS versus 1,280.0 GFLOPS, a difference of 0.666 TFLOPS. In percentage terms, the 64EU delivers 52.0 percent more FP32 throughput. Pixel rate follows the same ratio: 30.40 GPixel/s versus 20.00 GPixel/s, a 10.40 GPixel/s gap. Texture rate is 60.80 GTexel/s versus 40.00 GTexel/s, a 20.80 GTexel/s gap. These three metrics all scale with the doubled execution units, confirming that the 64EU is the stronger raw performer.

The 2 Xe Mobile’s wins are in clock speed and power. Its boost clock of 2500 MHz is 600 MHz higher than the 1900 MHz of the 64EU, a 31.6 percent advantage in frequency. Its TDP of 25 W is 40 W lower than the 64EU’s 65 W, meaning the 2 Xe Mobile uses 61.5 percent less power at its rated TDP. The 2 Xe Mobile also has 2 RT cores, while the 64EU has none listed, giving it an architectural feature advantage for ray tracing. The FP16 ratio is identical for both (2:1), but the absolute FP16 numbers favor the 64EU: 3.891 TFLOPS versus 2.560 TFLOPS.

The rival comparison for the 64EU shows a tight cluster. The Intel Arc Graphics 32EU and 24EU both score 733, producing a 0 percent delta, which indicates that within this Intel lineup, the 64EU does not outperform those lower-tier parts in the recorded Steel Nomad test. The AMD Radeon HD 6470M scores 723, a 1.4 percent deficit, and the NVIDIA GeForce GT 415M scores 751, a 2.4 percent surplus. The 64EU’s 733 score sits between those two older discrete GPUs. This context suggests that the 64EU’s performance is modest by current standards, ranking in the 3rd percentile of all GPUs. The 2 Xe Mobile has no comparable data, so its position relative to those rivals is unknown.

The boost clock difference is notable for the 2 Xe Mobile. A 2500 MHz boost on 256 shading units produces 1,280.0 GFLOPS, while the 64EU reaches 1.946 TFLOPS with 512 units at 1900 MHz. If the 2 Xe Mobile had the same 512-unit configuration, its FP32 would scale proportionally, but the database does not provide such a variant. The 2 Xe Mobile’s higher clock suggests the Xe3-LPG architecture is frequency-friendly, but the 64EU’s larger resource pool wins on absolute output.

Specification Differences

The two GPUs differ in every major specification category except memory and API support. The 2 Xe Mobile uses the Wildcat Lake chip with Xe3-LPG architecture, while the 64EU uses the Arrow Lake-S chip with Xe-LPG architecture. The process node is 3 nm for both, but the foundry differs: Intel for the 2 Xe Mobile and TSMC for the 64EU. The 64EU reports 17,800 million transistors on a 243 mm² die with a density of 73.3M per mm²; the 2 Xe Mobile reports unknown values for all three.

Shading units are 256 on the 2 Xe Mobile and 512 on the 64EU. TMUs are 16 versus 32. ROPs are 8 versus 16. RT cores are present on the 2 Xe Mobile (2) and absent on the 64EU. Tensor cores are null on both. Base clocks match at 300 MHz, but boost clocks differ: 2500 MHz for the 2 Xe Mobile and 1900 MHz for the 64EU. Pixel rate is 20.00 GPixel/s versus 30.40 GPixel/s. Texture rate is 40.00 GTexel/s versus 60.80 GTexel/s. FP32 is 1,280.0 GFLOPS versus 1.946 TFLOPS. FP16 is 2.560 TFLOPS versus 3.891 TFLOPS, both at 2:1.

TDP is 25 W for the 2 Xe Mobile and 65 W for the 64EU. Both use IGP slot width, but the bus interface differs: IGP for the 2 Xe Mobile and Ring Bus for the 64EU. Power connectors are listed as None for the 2 Xe Mobile and null for the 64EU. Display outputs are portable device dependent for the 2 Xe Mobile and motherboard dependent for the 64EU. Memory size, type, and bus width are System Shared on both, with System Dependent bandwidth. Release dates differ: the 2 Xe Mobile released on 2026-04-15, while the 64EU released on 2024-10-23. The 2 Xe Mobile’s predecessor is HD Graphics-M, and the 64EU’s predecessor is HD Graphics. Neither part has a successor or a launch MSRP in the database.

DETAILED SPECIFICATIONS

SPECIFICATION
Graphics 2 Xe Mobile
Graphics 64EU
Core Specs
Shading Units
256
512 +100.0%
Shaders
256
512 +100.0%
TMUs
16
32 +100.0%
ROPs
8
16 +100.0%
Execution Units
4
64 +1500.0%
Clocks
Base Clock
300 MHz
300 MHz
Boost Clock
2500 MHz
1900 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
20.00 GPixel/s
30.40 GPixel/s
Texture Rate
40.00 GTexel/s
60.80 GTexel/s
FP32 (TFLOPS)
1,280.0 GFLOPS
1.946 TFLOPS
FP64 (TFLOPS)
160.0 GFLOPS (1:8)
FP16 (TFLOPS)
2.560 TFLOPS (2:1)
3.891 TFLOPS (2:1)
AI/RT
RT Cores
2
XMX Cores
32
Power
TDP
25 W
65 W
TDP (W)
25
65 +160.0%
Power Connectors
None
Architecture
Architecture
Xe3-LPG
Xe-LPG
GPU Name
Wildcat Lake
Arrow Lake-S
Generation
Arc Graphics-M (Wildcat Lake)
Arc Graphics (Arrow Lake)
Process Size
3 nm
3 nm
Transistors
unknown
17,800 million
Die Size
unknown
243 mm²
Foundry
Intel
TSMC
Density
73.3M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
Shader Model
6.9
6.8
Physical
Slot Width
IGP
IGP
Outputs
Portable Device Dependent
Motherboard Dependent
Bus Interface
IGP
Ring Bus
Other
Production
Active
Active
Predecessor
HD Graphics-M
HD Graphics
View Arc Graphics 2 Xe Mobile Details View Arc Graphics 64EU Details