Intel Arc Graphics 48EU Mobile vs NVIDIA GeForce RTX 5090 SE Comparison

Intel Arc Graphics 48EU Mobile and NVIDIA GeForce RTX 5090 SE occupy opposite ends of the graphics spectrum. The former is an integrated processor from Intel’s Meteor Lake generation, while the latter is a discrete flagship from NVIDIA’s Blackwell 2.0 architecture. The database shows no shared benchmark scores for these two parts, and the head-to-head comparison records zero wins for either side. What follows is a specification and architecture analysis based solely on the recorded data.

Head-to-Head Benchmarks

The database contains no benchmark entries for either the Intel Arc Graphics 48EU Mobile or the NVIDIA GeForce RTX 5090 SE. Consequently, there are no recorded wins for either product in a direct comparison. The Intel part has a percentile rank of 50 among all GPUs, and the NVIDIA part also holds a percentile rank of 50. Neither product has an average benchmark score listed. The head-to-head section lists zero wins for both sides.

Without measured performance data, the comparison relies on theoretical specification limits. The NVIDIA GeForce RTX 5090 SE delivers 66.94 TFLOPS of FP32 compute, while the Intel Arc Graphics 48EU Mobile delivers 1,382.4 GFLOPS, which translates to 1.38 TFLOPS. The NVIDIA part is approximately 48 times faster in raw FP32 throughput. Pixel rate shows a similar gap: the RTX 5090 SE reaches 380.3 GPixel/s versus 14.40 GPixel/s for the Intel integrated solution. Texture rate differences are also stark, with the NVIDIA card producing 1,045.9 GTexel/s compared to 43.20 GTexel/s on the Intel part.

Memory bandwidth separates the two dramatically. The RTX 5090 SE uses 24 GB of GDDR7 memory on a 384-bit bus, achieving 1.34 TB/s. The Intel graphics uses system shared memory with system dependent bandwidth, and the memory clock is listed as system shared. The NVIDIA card’s memory clock is 1750 MHz with 28 Gbps effective speed.

The Verdict

The data indicates two products designed for entirely different workloads. The Intel Arc Graphics 48EU Mobile is an integrated GPU with a 28 W TDP, intended for portable devices where the display output is portable device dependent. The NVIDIA GeForce RTX 5090 SE is a dual-slot discrete card with a 500 W TDP, requiring a 900 W suggested power supply and a single 16-pin power connector.

Users requiring maximum compute throughput, high-resolution texture work, or ray tracing should select the NVIDIA part. The recorded data shows 110 RT cores and 440 tensor cores on the RTX 5090 SE, while the Intel part lists no RT cores or tensor cores. The NVIDIA card supports DirectX 12 Ultimate (12_2), while the Intel solution supports DirectX 12 (12_1). Both support OpenGL 4.6 and Vulkan 1.4.

The Intel part serves systems where power consumption and physical footprint are primary constraints. Its 28 W TDP and integrated form factor make it suitable for thin laptops. The NVIDIA part, with its 267 mm length, 111 mm height, and 40 mm width, requires substantial chassis space.

Architecture Differences

The Intel Arc Graphics 48EU Mobile uses the Xe-LPG architecture on a 10 nm process node, fabricated by Intel. It is part of the Meteor Lake chip, belonging to the Arc Graphics-M generation. The NVIDIA GeForce RTX 5090 SE uses Blackwell 2.0 architecture on a 5 nm process node, fabricated by TSMC. Its chip is designated GB202.

Transistor counts differ enormously. The NVIDIA GPU contains 92,200 million transistors on a 750 mm² die, yielding a transistor density of 122.9 million per square millimeter. The Intel part does not list transistor count, die size, or transistor density in the database.

The NVIDIA architecture includes 14,080 shading units, 440 texture mapping units, and 160 render output units. It also features 110 RT cores and 440 tensor cores. The Intel architecture has 384 shading units, 24 texture mapping units, and 8 render output units, with no dedicated RT or tensor cores listed.

The FP16 compute ratio reveals a key architectural difference. The Intel part achieves 2.765 TFLOPS FP16 using a 2:1 ratio relative to FP32, indicating shared execution resources. The NVIDIA part achieves 66.94 TFLOPS FP16 at a 1:1 ratio, meaning FP16 throughput matches FP32, a design choice that benefits mixed-precision workloads.

Specification Differences

The two products differ in nearly every measurable specification. The Intel part has a base clock of 300 MHz and a boost clock of 1800 MHz. The NVIDIA part has a base clock of 1740 MHz and a boost clock of 2377 MHz.

Memory configurations are fundamentally different. The Intel graphics uses system shared memory with a system shared bus width and system dependent bandwidth. The NVIDIA card uses 24 GB of GDDR7 memory with a 384-bit bus and 1.34 TB/s bandwidth.

The bus interface differs: the Intel part uses a Ring Bus, while the NVIDIA card uses PCIe 5.0 x16. The NVIDIA card’s display outputs are 1x HDMI 2.1b and 3x DisplayPort 2.1b, whereas the Intel part’s display outputs are portable device dependent.

Power requirements are vastly different. The Intel TDP is 28 W. The NVIDIA TDP is 500 W, with a suggested power supply of 900 W and one 16-pin power connector. The NVIDIA card is dual-slot; the Intel part is an IGP with no slot width applicable.

Physical dimensions are recorded only for the NVIDIA card: 267 mm length, 111 mm height, and 40 mm width. The Intel part has no recorded dimensions due to its integrated nature.

Release dates differ by two years. The Intel part launched on 2023-12-13. The NVIDIA part launched on 2025-12-31. The NVIDIA card has a launch MSRP of 1,499 USD, which is stated once per the database format. The Intel part has no launch MSRP.

The NVIDIA card has a predecessor in the GeForce 40 series and a successor in the GeForce 60 series. The Intel part lists HD Graphics-M as its predecessor and has no successor recorded.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The NVIDIA GeForce RTX 5090 SE delivers 66.94 TFLOPS FP32, compared to 1,382.4 GFLOPS (1.38 TFLOPS) for the Intel Arc Graphics 48EU Mobile.

Q: What memory types do these GPUs use?

A: The Intel Arc Graphics 48EU Mobile uses system shared memory with system dependent bandwidth. The NVIDIA GeForce RTX 5090 SE uses 24 GB of GDDR7 memory with a 384-bit bus and 1.34 TB/s bandwidth.

Q: Do both GPUs support the same DirectX version?

A: No. The Intel part supports DirectX 12 (12_1), while the NVIDIA part supports DirectX 12 Ultimate (12_2). Both support OpenGL 4.6 and Vulkan 1.4.

Q: What are the transistor counts for each GPU?

A: The NVIDIA GeForce RTX 5090 SE contains 92,200 million transistors. The Intel Arc Graphics 48EU Mobile has no transistor count listed in the database.

Q: Which GPU has ray tracing cores?

A: The NVIDIA GeForce RTX 5090 SE has 110 RT cores and 440 tensor cores. The Intel Arc Graphics 48EU Mobile lists no RT cores or tensor cores.

Q: How do the TDP values compare?

A: The Intel Arc Graphics 48EU Mobile has a TDP of 28 W. The NVIDIA GeForce RTX 5090 SE has a TDP of 500 W and requires a suggested power supply of 900 W.

Where Each One Wins

The Intel Arc Graphics 48EU Mobile wins in power efficiency and integration. Its 28 W TDP allows deployment in portable devices without discrete power connectors. The bus interface is a Ring Bus, and the display outputs depend on the portable device, indicating flexibility for laptop designs. The 10 nm process node from Intel and the Meteor Lake chip integration suit systems with tight thermal budgets. The lack of a listed power connector and PSU requirement confirms that no external power delivery is needed.

The NVIDIA GeForce RTX 5090 SE wins in raw compute, memory capacity, and feature support. The 66.94 TFLOPS FP32 and 66.94 TFLOPS FP16 figures enable demanding compute tasks. The 24 GB GDDR7 memory with 1.34 TB/s bandwidth supports large datasets and high-resolution textures. The 110 RT cores enable hardware-accelerated ray tracing, a feature absent from the Intel part. The 440 tensor cores provide AI acceleration capabilities.

The pixel rate of 380.3 GPixel/s on the NVIDIA card supports high refresh rate rendering at high resolutions. The texture rate of 1,045.9 GTexel/s handles complex material shading. The Intel part’s 14.40 GPixel/s and 43.20 GTexel/s suffice for basic display output and light 2D workloads.

The NVIDIA card’s PCIe 5.0 x16 interface provides high bandwidth to the host system. The Intel Ring Bus interface is designed for integrated memory access. The NVIDIA card’s dual-slot design with 267 mm length, 111 mm height, and 40 mm width requires a full-size chassis. The Intel IGP occupies no expansion slot.

The NVIDIA card supports DirectX 12 Ultimate, enabling advanced graphics features like mesh shaders and variable rate shading. The Intel part supports DirectX 12 (12_1), which covers the baseline feature set but lacks the Ultimate extensions. Both parts list the same OpenGL and Vulkan versions, so those APIs offer parity in version support.

The NVIDIA card’s release date of 2025-12-31 places it as a newer product than the Intel part’s 2023-12-13 launch. The NVIDIA card has a known successor, the GeForce 60 series, while the Intel part has no successor listed. The NVIDIA card’s predecessor is the GeForce 40 series; the Intel part’s predecessor is HD Graphics-M.

For systems where the GPU must fit within a 28 W power envelope and occupy no additional slots, the Intel Arc Graphics 48EU Mobile is the only choice between the two. For systems requiring maximum FP32 throughput, dedicated RT cores, tensor cores, and 24 GB of dedicated GDDR7 memory, the NVIDIA GeForce RTX 5090 SE is the clear option. The database does not contain any benchmark results to rank their real-world performance, so the verdict rests entirely on the specification deltas recorded above.