Intel Arc Graphics 128EU Mobile vs NVIDIA GeForce RTX 5090 SE Comparison

The Verdict

The database records two fundamentally different graphics solutions. The Intel Arc Graphics 128EU Mobile is an integrated processor (IGP) within the Meteor Lake chip, designed for portable devices. The NVIDIA GeForce RTX 5090 SE is a discrete, dual-slot add-in card built on the GB202 chip. The recorded data shows no head-to-head benchmark scores, no wins for either side, and no nearest rivals for comparison. The verdict must therefore rest on the specification differences and the architectural roles each part fulfills.

The RTX 5090 SE is in a different performance class entirely. Its FP32 throughput of 66.94 TFLOPS is approximately 14.5 times higher than the Arc's 4.608 TFLOPS. Its texture rate of 1,045.9 GTexel/s compares to 144.0 GTexel/s for the Intel part, a 7.3x advantage. The RTX 5090 SE also has dedicated ray tracing cores (110) and tensor cores (440), while the Intel Arc has none listed. For any workload involving ray tracing, AI acceleration, or high-resolution gaming, the NVIDIA part is the only viable option in this comparison.

The Intel Arc Graphics 128EU Mobile serves a different purpose. It is an IGP with a 28 W TDP, a 300 MHz base clock, and a 2250 MHz boost clock. It uses system-shared memory, meaning its performance is dependent on the host system's RAM. It is designed for basic graphics output, media playback, and light gaming on portable devices. Its 50th percentile ranking among all GPUs in the database indicates it sits in the middle of the performance distribution, but this ranking is based on its class of integrated graphics, not on comparison with a 500 W discrete card.

The RTX 5090 SE, with a 500 W TDP, a 900 W suggested PSU, and a 1,499 USD launch MSRP, is a high-end component for desktop systems. Its 24 GB of GDDR7 memory on a 384-bit bus delivers 1.34 TB/s of bandwidth. The Intel Arc has no dedicated memory; its bandwidth is described as "System Dependent." The RTX 5090 SE supports DirectX 12 Ultimate (12_2), while the Intel Arc supports DirectX 12 (12_1). The NVIDIA part also has a PCIe 5.0 x16 interface, while the Intel part uses a Ring Bus.

The data indicates that these two products should not be compared as direct competitors. The RTX 5090 SE is for users who need maximum performance in a desktop tower. The Intel Arc is for users who need a power-efficient integrated solution inside a laptop or compact device. The choice is not about which is better in absolute terms; it is about which fits the physical and power constraints of the intended system.

FAQ

Q: Which GPU has more shading units?

A: The NVIDIA GeForce RTX 5090 SE has 14,080 shading units. The Intel Arc Graphics 128EU Mobile has 1,024 shading units.

Q: What is the memory configuration of each product?

A: The RTX 5090 SE has 24 GB of GDDR7 memory on a 384-bit bus with 1.34 TB/s bandwidth. The Intel Arc uses System Shared memory with a System Dependent bandwidth.

Q: Does the Intel Arc support ray tracing?

A: The database lists no ray tracing cores for the Intel Arc Graphics 128EU Mobile. The RTX 5090 SE has 110 dedicated RT cores.

Q: What is the power consumption difference?

A: The Intel Arc has a 28 W TDP. The RTX 5090 SE has a 500 W TDP and requires a 900 W suggested power supply.

Q: Which product has a higher boost clock?

A: The RTX 5090 SE boosts to 2377 MHz. The Intel Arc boosts to 2250 MHz.

Q: What is the release date for each?

A: The Intel Arc Graphics 128EU Mobile was released on 2023-12-13. The RTX 5090 SE release date is 2025-12-31.

Architecture Differences

The two GPUs come from different architectural lineages. The Intel Arc Graphics 128EU Mobile uses the Xe-LPG architecture on a 10 nm process node from Intel's own foundry. It is part of the Meteor Lake chip generation, categorized under "Arc Graphics-M." This is an integrated graphics solution, meaning the GPU shares the physical package with the CPU and uses the system's main memory for its frame buffer.

The NVIDIA GeForce RTX 5090 SE is built on the Blackwell 2.0 architecture. It uses the GB202 chip, manufactured on a 5 nm process at TSMC. The chip has 92,200 million transistors on a 750 mm² die, giving it a transistor density of 122.9M per mm². This is a discrete GPU with its own dedicated memory subsystem.

The Intel part has no listed RT cores or tensor cores. Its shader pipeline consists of 1,024 shading units, 64 TMUs, and 32 ROPs. The NVIDIA part has 14,080 shading units, 440 TMUs, 160 ROPs, 110 RT cores, and 440 tensor cores. The presence of dedicated tensor cores on the RTX 5090 SE indicates support for AI-accelerated features, while the RT cores handle ray-traced rendering. The Intel Arc lacks both.

The memory architecture is another fundamental difference. The Intel Arc relies on system-shared memory, with the bus width also listed as "System Shared." The RTX 5090 SE uses 24 GB of GDDR7 on a 384-bit bus. The Intel part's memory clock is listed as "System Shared," while the NVIDIA part has a 1750 MHz memory clock with 28 Gbps effective speed.

The bus interfaces differ as well. The Intel Arc uses a Ring Bus, typical for integrated graphics connected to the CPU's internal fabric. The RTX 5090 SE uses PCIe 5.0 x16, a high-bandwidth external interface for discrete cards.

API support shows a minor difference. Both support OpenGL 4.6 and Vulkan 1.4. The Intel Arc supports DirectX 12 (12_1), while the RTX 5090 SE supports DirectX 12 Ultimate (12_2). The 12_2 feature level includes additional ray tracing and mesh shader capabilities.

The physical form factor also differs. The Intel Arc is an IGP, meaning it has no slot width, no power connectors, and no dimensions listed. The RTX 5090 SE is a dual-slot card measuring 267 mm in length, 111 mm in height, and 40 mm in width. It uses a single 16-pin power connector.

Specification Differences

The key specification differences are stark. The Intel Arc has a base clock of 300 MHz and a boost clock of 2250 MHz. The RTX 5090 SE has a base clock of 1740 MHz and a boost clock of 2377 MHz. The NVIDIA part runs faster at both ends of the clock spectrum.

The compute rates show the performance gap. The Intel Arc delivers 72.00 GPixel/s pixel rate and 144.0 GTexel/s texture rate. Its FP32 performance is 4.608 TFLOPS. The RTX 5090 SE delivers 380.3 GPixel/s pixel rate, 1,045.9 GTexel/s texture rate, and 66.94 TFLOPS FP32. The NVIDIA part is 5.3x faster in pixel rate, 7.3x faster in texture rate, and 14.5x faster in FP32.

The FP16 performance differs in ratio. The Intel Arc lists FP16 at 9.216 TFLOPS with a 2:1 ratio to FP32. The RTX 5090 SE lists FP16 at 66.94 TFLOPS with a 1:1 ratio. This means the NVIDIA part does not halve its throughput for FP16 workloads, while the Intel part doubles its FP32 throughput when doing FP16.

Memory capacity is a major differentiator. The Intel Arc has no dedicated memory; it uses system memory. The RTX 5090 SE has 24 GB of GDDR7. The memory bus width is 384-bit for the NVIDIA part, and the bandwidth is 1.34 TB/s. The Intel Arc's bandwidth is "System Dependent," which means it varies based on the host platform's memory configuration.

The power envelope is also different. The Intel Arc has a TDP of 28 W. The RTX 5090 SE has a TDP of 500 W. The suggested PSU for the NVIDIA part is 900 W. The Intel Arc, being an IGP, requires no separate power supply rating.

The display outputs differ. The Intel Arc uses "Portable Device Dependent" outputs, meaning the video connectors depend on the laptop or device design. The RTX 5090 SE has 1x HDMI 2.1b and 3x DisplayPort 2.1b outputs.

The release dates are far apart. The Intel Arc was released on 2023-12-13. The RTX 5090 SE has a release date of 2025-12-31. The Intel Arc's predecessor is HD Graphics-M. The RTX 5090 SE's predecessor is GeForce 40, and its successor is GeForce 60.

The process node difference is significant. The Intel Arc uses a 10 nm process at Intel. The RTX 5090 SE uses a 5 nm process at TSMC. The smaller process node allows for more transistors in the same area, which is reflected in the 92,200 million transistor count of the GB202 chip.

Head-to-Head Benchmarks

The database contains no head-to-head benchmark scores for these two products. The headToHeadBenchmarks field is empty. The winsA and winsB fields are both zero. There are no nearest rivals listed for either product. This means a direct performance comparison must be constructed from the recorded specification data.

The FP32 throughput is the most direct measure of raw compute capability. The RTX 5090 SE delivers 66.94 TFLOPS, which is 14.5 times the Intel Arc's 4.608 TFLOPS. This difference is so large that it defines the performance gap entirely.

The texture rate shows a similar story. The RTX 5090 SE processes 1,045.9 GTexel/s, while the Intel Arc manages 144.0 GTexel/s. A 7.3x difference in texture processing indicates that the NVIDIA part can handle far more complex geometry and texture filtering workloads.

The pixel rate difference is 380.3 GPixel/s versus 72.00 GPixel/s, a 5.3x advantage for the RTX 5090 SE. This affects fill-rate-bound scenarios, such as high-resolution rendering with heavy overdraw.

The RTX 5090 SE has 110 RT cores and 440 tensor cores. The Intel Arc has none. For ray-traced scenes or AI-based rendering features, the NVIDIA part has dedicated hardware that the Intel part lacks entirely.

Memory bandwidth is another decisive factor. The RTX 5090 SE has 1.34 TB/s of dedicated GDDR7 bandwidth. The Intel Arc's bandwidth is system dependent, which in practice is limited by the host laptop's shared memory interface, typically far below the discrete card's capability.

The clock speeds are closer than the compute rates. The Intel Arc boosts to 2250 MHz, while the RTX 5090 SE boosts to 2377 MHz. The Intel part's base clock of 300 MHz is much lower than the NVIDIA part's 1740 MHz base, but boost behavior matters more for sustained loads.

The power efficiency does not favor the comparison. The Intel Arc draws 28 W, the RTX 5090 SE draws 500 W. The RTX 5090 SE delivers roughly 14.5x the FP32 performance at roughly 17.9x the power draw. This means the Intel Arc is more efficient per watt for FP32, but the absolute performance is vastly different.

Where Each One Wins

The Intel Arc Graphics 128EU Mobile wins in power efficiency. Its 28 W TDP is suitable for thin-and-light laptops where battery life and thermal limits are primary constraints. The 300 MHz base clock and 2250 MHz boost clock operate within a tight power envelope.

The Intel Arc also wins on portability. It is an IGP with no slot width, no power connectors, and no separate card dimensions. It fits into any device that uses the Meteor Lake chip. Its display outputs are "Portable Device Dependent," which means they adapt to the host device's design.

The RTX 5090 SE wins in every performance category. Its 24 GB GDDR7 memory is essential for large datasets, high-resolution textures, and AI model loading. The 1.34 TB/s bandwidth supports high-throughput workloads.

The RTX 5090 SE wins in ray tracing. With 110 RT cores, it can handle real-time ray-traced effects that the Intel Arc cannot process at all. The 440 tensor cores enable DLSS-style upscaling and other AI features, which the Intel Arc lacks.

The NVIDIA part wins in connectivity. It offers PCIe 5.0 x16, a high-bandwidth interface for the host system. Its display outputs include HDMI 2.1b and DisplayPort 2.1b, supporting high refresh rates and multi-monitor setups.

The RTX 5090 SE wins in API support. Its DirectX 12 Ultimate (12_2) feature level includes advanced features like ray tracing and mesh shaders. The Intel Arc's DirectX 12 (12_1) lacks these capabilities.

For gaming, the RTX 5090 SE is the clear choice. Its 66.94 TFLOPS FP32, 380.3 GPixel/s pixel rate, and dedicated RT cores handle modern games at high settings. The Intel Arc can only manage light gaming workloads.

For productivity, the RTX 5090 SE's 24 GB memory and 440 tensor cores accelerate creative applications and AI workloads. The Intel Arc is limited to basic graphics acceleration and video playback.

For a desktop workstation or high-end gaming rig, the RTX 5090 SE is the only option that fits the requirements. For a portable device where battery life and low heat are priorities, the Intel Arc is the only option that fits the physical constraints.

The data shows no overlap in their intended use cases. The RTX 5090 SE is a high-performance discrete GPU for desktop systems. The Intel Arc is a low-power integrated GPU for mobile devices. Their roles in the market are defined by the systems they are designed for, not by direct competition with each other.