Intel Arc 140V Mobile vs NVIDIA GeForce RTX 5090 SE Comparison

Head-to-Head Benchmarks

The recorded data shows no direct head-to-head benchmark results between the Intel Arc 140V Mobile and the NVIDIA GeForce RTX 5090 SE. Both products sit at the 50th percentile in the database's all-GPU distribution, and neither has an average benchmark score recorded. This absence of measured results is itself informative: the two products occupy entirely separate segments, and any comparison must be drawn from their architectural specifications and recorded performance fields rather than direct competitive runs.

What the data does allow is a clear comparison of raw throughput ceilings. The RTX 5090 SE delivers 66.94 TFLOPS of FP32 compute, which is 16.8 times the Arc 140V Mobile's 3.994 TFLOPS. Texture rate follows the same pattern: 1,045.9 GTexel/s against 124.8 GTexel/s, an 8.4x advantage. Pixel throughput is less lopsided but still decisive, with the NVIDIA part reaching 380.3 GPixel/s versus 62.40 GPixel/s, a 6.1x margin.

Memory bandwidth tells the most extreme story. The RTX 5090 SE has 1.34 TB/s of dedicated GDDR7 bandwidth across a 384-bit bus. The Arc 140V Mobile uses system-shared memory with bandwidth described only as "System Dependent", meaning its effective throughput varies with the host platform's memory configuration. No fixed number can be assigned, but the structural difference is categorical: one part has a private, high-speed memory pool while the other borrows from the CPU's memory subsystem.

FP16 compute splits differently. The Arc 140V Mobile reaches 7.987 TFLOPS via a 2:1 ratio, doubling its FP32 figure. The RTX 5090 SE also doubles, but it runs at a 1:1 ratio, meaning its FP16 and FP32 both sit at 66.94 TFLOPS. The NVIDIA part still wins outright by a wide margin, but the Intel part's efficiency-oriented half-rate FP16 path is visible in the data.

Architecture Differences

The two chips come from different foundry nodes and different design philosophies. Intel's Arc 140V Mobile uses the Xe2-LPG architecture on a 3 nm TSMC process, as part of the Lunar Lake chip. NVIDIA's RTX 5090 SE uses Blackwell 2.0 on a 5 nm TSMC process, built around the GB202 chip. The process node difference is one generation apart in lithography, but the chip scales are not remotely comparable: the Intel die measures 172 mm² while the NVIDIA die measures 750 mm², a 4.4x difference in silicon area.

Transistor counts reinforce the scale gap. The RTX 5090 SE packs 92,200 million transistors, while the Arc 140V Mobile's count is listed as unknown. The NVIDIA part's transistor density of 122.9M per mm² can be derived from the known figures, but the Intel part lacks enough recorded data for comparison. What is clear is that the RTX 5090 SE is a large, high-power discrete GPU, while the Arc 140V Mobile is an integrated graphics processor with a 37 W TDP against the NVIDIA part's 500 W TDP.

Core configuration differences are structural. The Arc 140V Mobile has 1,024 shading units, 64 TMUs, 32 ROPs, and 8 ray tracing cores. The RTX 5090 SE has 14,080 shading units, 440 TMUs, 160 ROPs, and 110 ray tracing cores. The NVIDIA part also includes 440 tensor cores, a feature class entirely absent from the Intel part's recorded specifications.

Memory architecture diverges completely. The Arc 140V Mobile uses system-shared memory with no dedicated VRAM, a system-dependent bus width, and system-dependent bandwidth. The RTX 5090 SE uses 24 GB of GDDR7 on a 384-bit bus with 1.34 TB/s of bandwidth. The Intel part's memory clock is also listed as "System Shared", while the NVIDIA part runs at 1750 MHz with 28 Gbps effective.

The form factors reflect their intended roles. The Arc 140V Mobile is an IGP with no power connectors, no slot width beyond integrated, and no listed dimensions. The RTX 5090 SE is a dual-slot card measuring 267 mm by 111 mm by 40 mm, requiring a 16-pin power connector and a 900 W suggested PSU. The bus interfaces differ as well: IGP for Intel, PCIe 5.0 x16 for NVIDIA.

API support is identical on paper. Both parts list DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The display outputs differ, with the Intel part's outputs described as "Portable Device Dependent" and the NVIDIA part offering 1x HDMI 2.1b and 3x DisplayPort 2.1b.

FAQ

Q: Which processor has higher raw FP32 compute performance?

A: The NVIDIA GeForce RTX 5090 SE delivers 66.94 TFLOPS, which is 16.8 times the Intel Arc 140V Mobile's 3.994 TFLOPS.

Q: How do the memory systems compare?

A: The RTX 5090 SE uses 24 GB of GDDR7 on a 384-bit bus with 1.34 TB/s bandwidth. The Arc 140V Mobile relies on system-shared memory with system-dependent bandwidth and bus width.

Q: What are the power requirements for each?

A: The Arc 140V Mobile has a 37 W TDP and requires no power connectors. The RTX 5090 SE has a 500 W TDP, uses a 1x 16-pin connector, and has a 900 W suggested PSU.

Q: Do both support the same graphics APIs?

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

Q: Which has more ray tracing cores?

A: The RTX 5090 SE has 110 ray tracing cores. The Arc 140V Mobile has 8.

Q: What is the release timeline?

A: The Arc 140V Mobile was released on 2024-09-23. The RTX 5090 SE has a release date of 2025-12-31. The RTX 5090 SE carries a launch MSRP of 1,499 USD.

Specification Differences

| Field | Intel Arc 140V Mobile | NVIDIA GeForce RTX 5090 SE |

|---|---|---|

| Architecture | Xe2-LPG | Blackwell 2.0 |

| Process node | 3 nm | 5 nm |

| Die size | 172 mm² | 750 mm² |

| Transistors | unknown | 92,200 million |

| Transistor density | null | 122.9M / mm² |

| Base clock | 300 MHz | 1740 MHz |

| Boost clock | 1950 MHz | 2377 MHz |

| Memory | System Shared | 24 GB GDDR7 |

| Memory bus | System Shared | 384 bit |

| Memory bandwidth | System Dependent | 1.34 TB/s |

| Memory clock | System Shared | 1750 MHz, 28 Gbps effective |

| Shading units | 1024 | 14,080 |

| TMUs | 64 | 440 |

| ROPs | 32 | 160 |

| Ray tracing cores | 8 | 110 |

| Tensor cores | null | 440 |

| Pixel rate | 62.40 GPixel/s | 380.3 GPixel/s |

| Texture rate | 124.8 GTexel/s | 1,045.9 GTexel/s |

| FP32 | 3.994 TFLOPS | 66.94 TFLOPS |

| FP16 | 7.987 TFLOPS (2:1) | 66.94 TFLOPS (1:1) |

| TDP | 37 W | 500 W |

| Slot width | IGP | Dual-slot |

| Power connectors | null | 1x 16-pin |

| Suggested PSU | null | 900 W |

| Bus interface | IGP | PCIe 5.0 x16 |

| Display outputs | Portable Device Dependent | 1x HDMI 2.1b, 3x DisplayPort 2.1b |

| Dimensions | null | 267 mm, 111 mm, 40 mm |

| Release date | 2024-09-23 | 2025-12-31 |

| Predecessor | HD Graphics-M | GeForce 40 |

| Successor | null | GeForce 60 |

| Launch MSRP | null | 1,499 USD |

The Verdict

The data separates these two products so cleanly that the verdict writes itself. The Arc 140V Mobile is an integrated graphics solution for portable devices, built on a 3 nm process with a 37 W TDP and no dedicated memory. The RTX 5090 SE is a dual-slot, 500 W discrete graphics card with 24 GB of GDDR7, a 384-bit bus, and a 900 W suggested PSU. No benchmark results exist to complicate this picture, and the specification gaps are so large that no workload would plausibly close them.

The RTX 5090 SE is the clear choice for any task that requires maximum compute throughput, high-bandwidth memory, or heavy ray tracing. Its 110 ray tracing cores, 440 tensor cores, and 16.8x FP32 advantage over the Intel part place it in a different performance class entirely. The Arc 140V Mobile cannot compete on any measured specification, and the data does not suggest it should.

The Arc 140V Mobile's role is different. Its 3 nm process, 37 W TDP, and integrated form factor make it suitable for ultraportable systems where power consumption and physical space are the primary constraints. Its system-shared memory eliminates the need for dedicated VRAM, and its portable-device-dependent display outputs indicate a design target of laptops and compact devices rather than desktop workstations.

Where Each One Wins

The RTX 5090 SE wins in every compute-intensive category recorded. FP32 throughput, texture rate, pixel rate, ray tracing core count, tensor core count, memory capacity, memory bandwidth, and memory bus width all favor the NVIDIA part by wide margins. Its 1.34 TB/s of bandwidth is more than any system-shared configuration could realistically provide to the Intel IGP. For rendering, machine learning inference, or any workload that saturates memory bandwidth, the data points unambiguously to the RTX 5090 SE.

The Arc 140V Mobile wins in power efficiency and integration. Its 37 W TDP is 13.5 times lower than the RTX 5090 SE's 500 W TDP. It requires no power connectors, no auxiliary cooling beyond what the host device provides, and no dedicated PSU. Its 3 nm process node is a generation ahead of the NVIDIA part's 5 nm node, which contributes to this efficiency. The Intel part's IGP bus interface means it occupies no expansion slot and adds no physical footprint to a system.

The release timeline also separates the products. The Arc 140V Mobile launched on 2024-09-23, over a year before the RTX 5090 SE's 2025-12-31 release date. The NVIDIA part's predecessor is the GeForce 40 series, and its successor is listed as GeForce 60, confirming its position as a high-end discrete offering. The Intel part's predecessor is HD Graphics-M, and no successor is recorded, indicating it sits at the top of the integrated graphics stack rather than in the discrete segment.

The data does not support a single "better" product. It supports two different products for two different physical and power envelopes. The RTX 5090 SE is the only choice for maximum performance per the recorded specifications. The Arc 140V Mobile is the only choice for a 37 W integrated solution with no dedicated memory requirement. Any other interpretation would require benchmark data that the database does not currently contain.