Intel Arc Graphics 1 Xe Mobile vs NVIDIA GeForce RTX 5090 SE Comparison

The Intel Arc Graphics 1 Xe Mobile and the NVIDIA GeForce RTX 5090 SE occupy opposite extremes of the graphics hardware spectrum. The database records no shared benchmark entries, so direct performance comparisons must rely on the specification deltas and architectural positioning. The Intel part is an integrated graphics solution for portable devices, while the NVIDIA part is a discrete flagship designed for maximum throughput. The data shows that every measurable compute, memory, and rendering metric favors the RTX 5090 SE, but each product serves a distinct use case defined by power, physical footprint, and system integration.

Head-to-Head Benchmarks

The database contains no overlapping benchmark scores for these two products. The Intel Arc Graphics 1 Xe Mobile has an empty benchmark list, and the NVIDIA GeForce RTX 5090 SE also has an empty benchmark list. As a result, the head-to-head comparison must be derived from the recorded specification data rather than from executed workloads.

The most significant single metric difference is FP32 throughput. The RTX 5090 SE delivers 66.94 TFLOPS, while the Intel part delivers 588.8 GFLOPS, which converts to 0.5888 TFLOPS. The NVIDIA part is approximately 113.7 times higher in raw single-precision compute. In FP16, the RTX 5090 SE also achieves 66.94 TFLOPS with a 1:1 ratio, while the Intel part reaches 1,177.6 GFLOPS with a 2:1 ratio, meaning the Intel figure is halved for true FP16 throughput, resulting in roughly 588.8 GFLOPS effective. The NVIDIA part outperforms by a factor close to 113.7 as well.

Texture rate shows a similar chasm. The RTX 5090 SE records 1,045.9 GTexel/s, while the Intel part records 18.40 GTexel/s, a difference of about 56.8 times. Pixel rate favors NVIDIA at 380.3 GPixel/s versus 9.200 GPixel/s, a 41.3 times advantage. These ratios indicate that the RTX 5090 SE can fill geometry and texture workloads at rates that the Intel integrated solution cannot approach.

The memory subsystem reinforces the gap. The RTX 5090 SE has 24 GB of GDDR7 memory on a 384-bit bus, delivering 1.34 TB/s of bandwidth. The Intel part uses System Shared memory, with bandwidth described as System Dependent and no fixed capacity or bus width. In any configuration, shared system memory bandwidth will fall far short of dedicated GDDR7. The data implies a bandwidth ratio that is not numerically specified for the Intel side, but the 1.34 TB/s figure stands as the only concrete bandwidth number, and it belongs to the NVIDIA part.

Clock rates show a narrower relative difference. The Intel base clock is 300 MHz with a boost of 2300 MHz. The NVIDIA base clock is 1740 MHz with a boost of 2377 MHz. The boost clocks are close, but the Intel part operates at a much lower base frequency, and its 128 shading units must process all work across a fraction of the 14,080 shading units on the NVIDIA chip. The RTX 5090 SE also has 440 texture mapping units versus 8, and 160 raster operations pipelines versus 4.

The RTX 5090 SE includes 110 ray tracing cores and 440 tensor cores. The Intel part has 1 ray tracing core and no tensor cores listed. This difference is structural, not merely quantitative.

Architecture Differences

The Intel Arc Graphics 1 Xe Mobile uses the Xe3-LPG architecture, built on Wildcat Lake, and belongs to the Arc Graphics-M (Wildcat Lake) generation. The process node is 3 nm, fabricated by Intel. The NVIDIA GeForce RTX 5090 SE uses the Blackwell 2.0 architecture, built on the GB202 chip, belonging to the GeForce 50 series. The process node is 5 nm, fabricated by TSMC. The transistor counts differ substantially: the Intel die size and transistor count are listed as unknown, while the RTX 5090 SE has 92,200 million transistors on a 750 mm² die, with a transistor density of 122.9M per mm².

The Intel part has 128 shading units, 8 TMUs, and 4 ROPs. The NVIDIA part has 14,080 shading units, 440 TMUs, and 160 ROPs. The RTX 5090 SE also includes dedicated tensor cores (440) and ray tracing cores (110), while the Intel part lists a single ray tracing core and no tensor cores. The Intel part supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, exactly matching the NVIDIA API support. Both report the same API versions, so software compatibility is equal on that front.

The power envelope is a major architectural differentiator. The Intel part is rated at 25 W TDP and uses no power connectors, being an IGP (integrated graphics processor) with a bus interface of IGP. The NVIDIA part is rated at 500 W TDP, uses a 1x 16-pin power connector, and requires a suggested 900 W power supply. The slot width is Dual-slot for NVIDIA, while Intel is listed as IGP. The physical dimensions for NVIDIA are 267 mm in length, 111 mm in height, and 40 mm in width. The Intel part has no listed dimensions because it is integrated into a portable device.

The memory architecture is fundamentally different. The Intel part uses System Shared memory, meaning it borrows from the host system's RAM. The NVIDIA part has dedicated 24 GB of GDDR7 with a 384-bit bus and 1.34 TB/s bandwidth. The memory clock for NVIDIA is 1750 MHz with 28 Gbps effective, while the Intel memory clock is listed as System Shared with System Dependent bandwidth.

The release dates are close. The NVIDIA part was released on 2025-12-31, and the Intel part on 2026-04-15. The NVIDIA part has a predecessor of GeForce 40 and a successor of GeForce 60. The Intel part has a predecessor of HD Graphics-M and no successor listed. The production status for both is Active.

The Verdict

The data indicates that the RTX 5090 SE is designed for workloads that require extreme compute, high memory bandwidth, and dedicated hardware for ray tracing and tensor operations. The Intel Arc Graphics 1 Xe Mobile is designed for low-power integrated use in portable devices, where the 25 W TDP and lack of external power connectors are essential. No benchmark scores exist to compare real-world performance, but the specification deltas are so large that the RTX 5090 SE is categorically faster in every recorded metric.

For a user who needs to run GPU-accelerated rendering, high-resolution gaming, or machine learning inference, the RTX 5090 SE is the only viable choice based on the recorded data. Its 24 GB memory, 1.34 TB/s bandwidth, and 66.94 TFLOPS FP32 throughput provide the necessary resources. The Intel part cannot match these figures and would be constrained by system-shared memory and a 588.8 GFLOPS ceiling.

For a user who needs a graphics solution inside a thin, portable device with no discrete GPU slot, the Intel part is the only option in this comparison. Its 25 W TDP, IGP form factor, and no power connector requirement fit that use case. The RTX 5090 SE requires a 500 W TDP, a 900 W power supply, a dual-slot physical space, and a 16-pin connector, none of which fit a portable device.

The choice is not about one being better than the other; it is about which environment the hardware targets. The RTX 5090 SE belongs in a desktop with a high-capacity power supply. The Intel part belongs in a laptop or handheld where power draw and physical space are at a premium. The percentileVsAllGpus field records both at 50, which indicates a median position in the database distribution, but that metric is not meaningful when the two products have no shared benchmarks and target entirely different market segments.

Specification Differences

The database records the following fields where the two parts differ:

• Manufacturer: Intel versus NVIDIA
• Chip: Wildcat Lake versus GB202
• Architecture: Xe3-LPG versus Blackwell 2.0
• Generation: Arc Graphics-M (Wildcat Lake) versus GeForce 50
• Process Node: 3 nm versus 5 nm
• Foundry: Intel versus TSMC
• Transistors: unknown versus 92,200 million
• Die Size: unknown versus 750 mm²
• Transistor Density: not listed versus 122.9M / mm²
• Base Clock: 300 MHz versus 1740 MHz
• Boost Clock: 2300 MHz versus 2377 MHz
• Memory Clock: System Shared versus 1750 MHz 28 Gbps effective
• Memory Size: System Shared versus 24 GB
• Memory Type: System Shared versus GDDR7
• Memory Bus Width: System Shared versus 384 bit
• Memory Bandwidth: System Dependent versus 1.34 TB/s
• Shading Units: 128 versus 14,080
• TMUs: 8 versus 440
• ROPs: 4 versus 160
• Ray Tracing Cores: 1 versus 110
• Tensor Cores: not listed versus 440
• Pixel Rate: 9.200 GPixel/s versus 380.3 GPixel/s
• Texture Rate: 18.40 GTexel/s versus 1,045.9 GTexel/s
• FP32: 588.8 GFLOPS versus 66.94 TFLOPS
• FP16: 1,177.6 GFLOPS (2:1) versus 66.94 TFLOPS (1:1)
• TDP: 25 W versus 500 W
• Slot Width: IGP versus Dual-slot
• Power Connectors: None versus 1x 16-pin
• Suggested PSU: not listed versus 900 W
• Bus Interface: IGP versus PCIe 5.0 x16
• Display Outputs: Portable Device Dependent versus 1x HDMI 2.1b3x DisplayPort 2.1b
• Dimensions: not listed versus 267 mm 10.5 inches length, 111 mm 4.4 inches height, 40 mm 1.6 inches width
• Release Date: 2026-04-15 versus 2025-12-31
• Predecessor: HD Graphics-M versus GeForce 40
• Successor: not listed versus GeForce 60
• Launch MSRP: not listed versus 1,499 USD

The API support is identical: DirectX 12 Ultimate (12_2), OpenGL 4.6, Vulkan 1.4 for both.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The NVIDIA GeForce RTX 5090 SE records 66.94 TFLOPS FP32, while the Intel Arc Graphics 1 Xe Mobile records 588.8 GFLOPS, which is 0.5888 TFLOPS. The NVIDIA part is about 113.7 times higher.

Q: Does the Intel Arc Graphics 1 Xe Mobile support ray tracing?

A: The database lists 1 ray tracing core for the Intel Arc Graphics 1 Xe Mobile. The NVIDIA GeForce RTX 5090 SE lists 110 ray tracing cores. Both support DirectX 12 Ultimate (12_2), which includes ray tracing features.

Q: What is the memory configuration for each GPU?

A: The Intel Arc Graphics 1 Xe Mobile uses System Shared memory with System Dependent bandwidth. The NVIDIA GeForce RTX 5090 SE has 24 GB of GDDR7 on a 384-bit bus with 1.34 TB/s bandwidth and a memory clock of 1750 MHz 28 Gbps effective.

Q: What are the power requirements for each GPU?

A: The Intel Arc Graphics 1 Xe Mobile has a 25 W TDP, no power connectors, and no suggested PSU. The NVIDIA GeForce RTX 5090 SE has a 500 W TDP, a 1x 16-pin power connector, and a suggested 900 W power supply.

Q: Which GPU was released first according to the database?

A: The NVIDIA GeForce RTX 5090 SE has a release date of 2025-12-31. The Intel Arc Graphics 1 Xe Mobile has a release date of 2026-04-15. The NVIDIA part was released earlier.

Q: Do both GPUs support the same graphics APIs?

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

Where Each One Wins

The Intel Arc Graphics 1 Xe Mobile wins in power efficiency and integration. Its 25 W TDP compares to the 500 W TDP of the NVIDIA part, a 20 times lower power draw. The Intel part requires no power connectors and uses an IGP bus interface, meaning it fits inside a portable device without dedicated power cabling. The slot width is listed as IGP, indicating no expansion slot is needed. The NVIDIA part requires a dual-slot physical space, a 16-pin connector, and a 900 W power supply, making it unsuitable for portable or low-power systems. The Intel part also has no listed dimensions, which aligns with an integrated design where the GPU is embedded into the host processor package.

The NVIDIA GeForce RTX 5090 SE wins in every raw performance category. The FP32 throughput is 66.94 TFLOPS versus 588.8 GFLOPS. The texture rate is 1,045.9 GTexel/s versus 18.40 GTexel/s. The pixel rate is 380.3 GPixel/s versus 9.200 GPixel/s. The memory bandwidth is 1.34 TB/s versus System Dependent (no fixed figure). The shading units number 14,080 versus 128. The ray tracing cores number 110 versus 1. The tensor cores number 440 versus none listed. The NVIDIA part has 24 GB of dedicated GDDR7 memory, while the Intel part relies on shared system memory with no dedicated capacity.

For use cases from the data, the NVIDIA part wins for high-end gaming, 3D rendering, AI inference, and any workload that can utilize its 440 tensor cores and 110 ray tracing cores. The Intel part wins for basic graphics output in a low-power portable device, where the 25 W TDP and no external power requirement are the decisive factors. The release dates are close, but the NVIDIA part comes with a launch MSRP of 1,499 USD, while the Intel part has no listed MSRP, consistent with its integrated nature.