Intel Arc 130V Mobile vs NVIDIA GeForce RTX 5070 SUPER Comparison

FAQ

Q: What are the fundamental positioning differences between the Intel Arc 130V Mobile and the NVIDIA GeForce RTX 5070 SUPER?

A: The Intel Arc 130V Mobile is an integrated graphics processor (IGP) from the Lunar Lake generation, built on a 3 nm process with a 37 W TDP, designed for portable devices. The NVIDIA GeForce RTX 5070 SUPER is a discrete, dual-slot add-in card from the GeForce 50-series, built on a 5 nm process with a 275 W TDP, designed for desktop systems.

Q: How do the two compare in raw pixel throughput?

A: The RTX 5070 SUPER delivers a pixel rate of 201.0 GPixel/s, which is approximately 3.9 times higher than the Intel Arc 130V Mobile's 51.80 GPixel/s. The NVIDIA part also achieves a texture rate of 502.4 GTexel/s versus 103.6 GTexel/s for the Intel part.

Q: What do the recorded benchmark scores indicate about performance ranking?

A: The RTX 5070 SUPER has a recorded 3DMark Steel Nomad DX12 score of 2690, placing it at the 18th percentile among all GPUs in the database. The Intel Arc 130V Mobile has no recorded benchmark scores and sits at the 50th percentile, meaning its actual competitive position is not established by direct measurements.

Q: Which GPUs sit closest to the RTX 5070 SUPER in the database records?

A: The nearest rivals to the RTX 5070 SUPER are the NVIDIA Quadro K1100M (average score 2664, 1% difference), the NVIDIA GeForce GT 1030 (2662, 1.1% difference), the Intel Arc Pro B50 (2660, 1.1% difference), and the NVIDIA GeForce GT 440 (2645, 1.7% difference). These are all within a narrow band of the RTX 5070 SUPER's 2690 score.

Q: What are the memory configurations for each product?

A: The RTX 5070 SUPER uses 18 GB of GDDR7 memory on a 192-bit bus with 672.0 GB/s of bandwidth. The Intel Arc 130V Mobile uses system-shared memory, with a system-dependent bus width and bandwidth, and its memory clock is listed as "System Shared" as well.

Q: How do the API support levels compare?

A: Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The feature-level API compatibility is identical between the two, despite the large architectural and performance differences.

Where Each One Wins

The recorded data divides the two products into separate spheres of use. The Intel Arc 130V Mobile, with its 37 W TDP and integrated design, is the only option for systems where a discrete card cannot be installed. Its IGP bus interface and portable-device-dependent display outputs tie it directly to laptops and compact form factors. The 3 nm process node from TSMC gives it a manufacturing advantage in density per watt, which suits power-constrained environments.

The NVIDIA GeForce RTX 5070 SUPER wins on every absolute performance metric in the database. Its FP32 throughput of 32.15 TFLOPS is roughly 9.7 times the Intel part's 3.315 TFLOPS. It has 6400 shading units versus 896, 200 texture mapping units versus 56, 80 ROPs versus 28, 50 RT cores versus 7, and 200 tensor cores where the Intel part lists none. The 18 GB GDDR7 frame buffer with 672.0 GB/s bandwidth is a dedicated memory subsystem, while the Intel part relies on system memory with dependent bandwidth. For applications that fit into a desktop chassis with a PCIe 5.0 x16 slot and a 275 W power envelope, the RTX 5070 SUPER is the clear performer.

The use-case split is simple: the integrated part wins on integration and low power, the discrete part wins on every measurable performance category. There is no overlap in the data where the Intel part beats NVIDIA on speed. The only recorded benchmark score belongs to the RTX 5070 SUPER.

Architecture Differences

The two GPUs come from different architectural families. Intel uses Xe2-LPG, the low-power graphics variant of its Xe2 architecture, implemented on the Lunar Lake chip. NVIDIA uses Blackwell 2.0, its current high-performance architecture, on the GB205 chip. The process nodes differ: Intel is on 3 nm TSMC, NVIDIA is on 5 nm TSMC. The Intel die measures 172 mm², while the NVIDIA die measures 263 mm². NVIDIA's transistor count is listed at 31,100 million with a density of 118.3M per mm²; Intel's transistor count is unknown.

The compute layouts differ sharply. Intel fields 896 shading units, 56 TMUs, 28 ROPs, and 7 RT cores. NVIDIA fields 6400 shading units, 200 TMUs, 80 ROPs, 50 RT cores, and 200 tensor cores. The Intel part has no tensor core count listed; the NVIDIA part includes tensor cores as a distinct hardware block. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so the API surface is the same even though the underlying hardware is not.

The FP16 execution mode also differs. Intel lists FP16 at 6.630 TFLOPS (2:1), meaning it halves the rate for FP16 relative to FP32. NVIDIA lists FP16 at 32.15 TFLOPS (1:1), meaning it sustains the same rate as FP32. That is a meaningful architectural choice: NVIDIA's Blackwell 2.0 design treats FP16 as a first-class throughput mode, while Intel's Xe2-LPG treats it as a reduced-rate mode.

The memory architecture is fundamentally different. NVIDIA uses a dedicated GDDR7 interface with a 192-bit bus and 672.0 GB/s bandwidth. Intel uses system-shared memory, so the bus width, bandwidth, and memory clock are all dependent on the host platform. The NVIDIA card has a 1750 MHz memory clock (28 Gbps effective), while Intel lists "System Shared" for its memory clock.

Specification Differences

The two products differ across nearly every specification field. The Intel Arc 130V Mobile has a base clock of 300 MHz and a boost clock of 1850 MHz. The NVIDIA RTX 5070 SUPER has a base clock of 2325 MHz and a boost clock of 2512 MHz. The NVIDIA base clock is higher than the Intel boost clock by 475 MHz.

Process node: Intel 3 nm, NVIDIA 5 nm, both TSMC. Die size: Intel 172 mm², NVIDIA 263 mm². Transistors: NVIDIA 31,100 million, Intel unknown. Transistor density: NVIDIA 118.3M per mm², Intel not listed.

Shading units: 896 versus 6400. TMUs: 56 versus 200. ROPs: 28 versus 80. RT cores: 7 versus 50. Tensor cores: none listed versus 200. Pixel rate: 51.80 GPixel/s versus 201.0 GPixel/s. Texture rate: 103.6 GTexel/s versus 502.4 GTexel/s. FP32: 3.315 TFLOPS versus 32.15 TFLOPS. FP16: 6.630 TFLOPS (2:1) versus 32.15 TFLOPS (1:1).

TDP: 37 W versus 275 W. Slot width: IGP versus dual-slot. Power connectors: none versus 1x 16-pin. Bus interface: IGP versus PCIe 5.0 x16. Display outputs: portable-device-dependent versus 1x HDMI 2.1b and 3x DisplayPort 2.1b. Dimensions: not listed for Intel; NVIDIA is 245 mm long, 115 mm high, and 40 mm wide.

Release dates: Intel on 2024-09-23, NVIDIA on 2025-12-31. Production status for both is Active. No launch MSRP is listed for either product.

Head-to-Head Benchmarks

There is only one recorded benchmark in the database. The NVIDIA GeForce RTX 5070 SUPER scores 2690 in 3DMark Steel Nomad DX12. The Intel Arc 130V Mobile has no recorded benchmarks and an average benchmark score of 0. This means the data cannot show a direct head-to-head score comparison; it can only show that one side has a measured result and the other does not.

The RTX 5070 SUPER's 2690 score places it at the 18th percentile among all GPUs. Its nearest rivals in the database are all within 1.7% of its score. The NVIDIA Quadro K1100M sits at 2664 (1% lower), the GeForce GT 1030 at 2662 (1.1% lower), the Intel Arc Pro B50 at 2660 (1.1% lower), and the GeForce GT 440 at 2645 (1.7% lower). This cluster indicates that the RTX 5070 SUPER's measured performance, despite its high-end specifications, lands in a crowded mid-range band in this particular test.

The computed rates tell a different story than the benchmark cluster. The FP32 throughput difference is roughly 9.7 times in NVIDIA's favor. The pixel rate difference is roughly 3.9 times. The texture rate difference is roughly 4.8 times. The RT core count differs by a factor of roughly 7.1. The memory bandwidth difference is enormous: 672.0 GB/s versus a system-dependent figure that the database does not quantify.

The absence of Intel benchmark data limits the comparison. The database records the Intel part at the 50th percentile, but with an average benchmark score of 0, that percentile does not correspond to a measured performance level. The RTX 5070 SUPER's percentile of 18 is based on its actual 2690 score. The data indicates that the Intel part has no verified performance record, while the NVIDIA part has one, and that one places it near several older or lower-tier discrete cards.

The Verdict

The data supports only one allocation of roles. The Intel Arc 130V Mobile is an integrated GPU for portable devices, with a 37 W TDP, a 3 nm process, and system-shared memory. It has no recorded benchmark score, no discrete memory, and no tensor core count. It is appropriate for systems where a discrete GPU cannot be installed.

The NVIDIA GeForce RTX 5070 SUPER is a discrete, dual-slot card with a 275 W TDP, 18 GB of GDDR7 memory, 6400 shading units, 200 tensor cores, and a 672.0 GB/s memory interface. It has a recorded 3DMark Steel Nomad DX12 score of 2690, which places it at the 18th percentile, near the Quadro K1100M, GT 1030, Arc Pro B50, and GT 440 in the database records.

The choice between them depends entirely on the system form factor and power budget. For a portable device with an IGP bus interface, the Intel part is the only option in this comparison. For a desktop with a PCIe 5.0 x16 slot, a 1x 16-pin power connector, and a 275 W power budget, the NVIDIA part delivers all of the measured performance. The data does not suggest any scenario where the Intel part outperforms the NVIDIA part on a recorded metric, because the Intel part has no recorded metrics. The NVIDIA part wins every category where a number exists.