Intel Arc 130T Mobile vs NVIDIA Rubin GPU Comparison

Head-to-Head Benchmarks

The database records no direct head-to-head benchmark entries for the Intel Arc 130T Mobile and the NVIDIA Rubin GPU. Both products carry a percentile ranking of 50 against all GPUs in the database, and each has an average benchmark score of zero. This absence of measured performance data means the comparison must rely entirely on architectural specifications and computed throughput rates rather than observed workloads.

The raw compute figures separate the two decisively. The NVIDIA Rubin GPU delivers 130.0 TFLOPS of FP32 throughput, while the Intel Arc 130T Mobile produces 3.942 TFLOPS. That places the Rubin at roughly 33 times the FP32 output of the Arc part. In FP16, the gap narrows slightly in proportional terms but remains enormous: Rubin reaches 260.0 TFLOPS against 7.885 TFLOPS for the Arc. The texture rate tells a similar story. Rubin processes 2,031.2 GTexel/s, while the Arc achieves 123.2 GTexel/s. Interestingly, the pixel rate flips in favor of Intel. The Arc 130T Mobile records 61.60 GPixel/s, and the Rubin GPU records 54.41 GPixel/s, a modest Intel advantage of about 7 GPixel/s despite the Rubin's otherwise dominant position.

These numbers indicate that the Rubin GPU is designed for a completely different performance class. The FP32 and texture throughput differences are so large that no workload category would plausibly bring the Arc within reach. The pixel rate exception is curious. The Rubin's 24 ROPs versus the Arc's 28 ROPs, combined with the Arc's 2200 MHz boost clock versus Rubin's 2267 MHz boost, explains the small reversal. The Rubin's higher boost clock nearly compensates for its lower ROP count, but not quite.

Where Each One Wins

The Intel Arc 130T Mobile wins in pixel throughput. Its 61.60 GPixel/s exceeds the Rubin's 54.41 GPixel/s, which is a useful advantage for rasterization-bound tasks that depend on fill rate. The Arc also supports a full DirectX 12 Ultimate feature set with API version 12_2, OpenGL 4.6, and Vulkan 1.4. The Rubin GPU lists N/A for all three graphics APIs. For any conventional graphics workload, the Arc has the only functional API path.

The NVIDIA Rubin GPU wins in every compute-heavy category. Its 28672 shading units dwarf the Arc's 896. The Rubin also fields 896 tensor cores, whereas the Arc lists none. The memory subsystem is another decisive win. Rubin carries 288 GB of HBM4 memory across a 16384-bit bus, delivering 22.1 TB/s of bandwidth. The Arc uses system shared memory with bandwidth listed as system dependent, which means its effective bandwidth is whatever the host platform provides. The Rubin's memory clock runs at 2695 MHz with 10.8 Gbps effective data rate, while the Arc's memory clock is system shared.

The process technology also favors the Rubin. The Rubin GPU is built on a 3 nm process at TSMC, while the Arc uses a 5 nm process, also at TSMC. The Rubin's die is 1456 mm² with 336,000 million transistors, giving a transistor density of 230.8M per mm². The Arc's transistor count and die size are listed as unknown. The Rubin's TDP of 2300 W indicates power delivery is not constrained, while the Arc's 35 W TDP places it in an entirely different power envelope.

The Verdict

The data places these two products in separate market segments with no meaningful overlap. The Intel Arc 130T Mobile is an integrated graphics processor for portable devices, with its display outputs listed as portable device dependent and its bus interface as IGP. The NVIDIA Rubin GPU is a server-class accelerator on an SXM module with PCIe 6.0 x16 connectivity and no display outputs. The Rubin is the predecessor to Server Blackwell, while the Arc has the HD Graphics-M as its predecessor.

For a user requiring graphics API support, the Arc is the only option of the two. Its DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4 support make it functional for rendering workloads. For compute throughput, the Rubin is overwhelmingly stronger, with 130.0 TFLOPS FP32 and 260.0 TFLOPS FP16. The 22.1 TB/s memory bandwidth further cements its position for data-intensive tasks. The release dates also differ: the Arc launched in January 2025, and the Rubin is dated for December 2025. Neither product has a launch MSRP recorded in the database.

FAQ

Q: Which GPU has higher FP32 performance?

A: The NVIDIA Rubin GPU delivers 130.0 TFLOPS, compared to the Intel Arc 130T Mobile's 3.942 TFLOPS.

Q: Does the Intel Arc 130T Mobile support DirectX 12 Ultimate?

A: Yes, it lists DirectX 12 Ultimate (12_2), along with OpenGL 4.6 and Vulkan 1.4. The NVIDIA Rubin GPU lists N/A for DirectX, OpenGL, and Vulkan.

Q: What memory configuration does each GPU use?

A: The Rubin GPU uses 288 GB of HBM4 on a 16384-bit bus with 22.1 TB/s bandwidth. The Arc 130T Mobile uses system shared memory, with system dependent bandwidth.

Q: Which GPU has more shading units?

A: The NVIDIA Rubin GPU has 28672 shading units. The Intel Arc 130T Mobile has 896.

Q: What is the pixel rate for each GPU?

A: The Arc 130T Mobile records 61.60 GPixel/s. The Rubin GPU records 54.41 GPixel/s.

Q: What are the process nodes for these GPUs?

A: The Rubin GPU uses a 3 nm TSMC process. The Arc 130T Mobile uses a 5 nm TSMC process.

Architecture Differences

The two GPUs come from different architectural families. The Intel Arc 130T Mobile uses the Xe-LPG+ architecture on the Arrow Lake-H chip, belonging to the Arc Graphics-M (Arrow Lake) generation. The NVIDIA Rubin GPU uses the Rubin architecture on the GR100 chip, part of the Server Rubin (Rxx) generation.

The Arc integrates 7 ray tracing cores and 896 shading units, with 56 texture mapping units and 28 ROPs. The Rubin does not list ray tracing cores in the database, but it includes 896 tensor cores and 24 ROPs. The Arc lists no tensor cores. This structural difference indicates the Rubin is oriented toward tensor and matrix workloads, while the Arc carries dedicated ray tracing hardware.

The memory architectures diverge completely. The Arc uses system shared memory, meaning the GPU has no dedicated VRAM and depends on the host system. The Rubin uses 288 GB of HBM4 with a 16384-bit bus. The Rubin's 22.1 TB/s bandwidth is a fixed specification, while the Arc's bandwidth is system dependent.

The process and packaging also differ. The Rubin is manufactured on TSMC's 3 nm node, with a 1456 mm² die and 336,000 million transistors. The Arc uses TSMC's 5 nm node, with its transistor count and die size recorded as unknown. The Rubin's transistor density of 230.8M per mm² is the only density figure in the database. The production status for both is active, and neither lists a successor.

The Rubin is a server accelerator with an SXM module slot width and PCIe 6.0 x16 interface. The Arc is an integrated GPU with an IGP bus interface and portable device dependent display outputs. The Rubin has no display outputs at all. The Rubin's predecessor is Server Blackwell, while the Arc's predecessor is HD Graphics-M.

Specification Differences

The specification differences between the two are extensive. The Intel Arc 130T Mobile has a base clock of 300 MHz and a boost clock of 2200 MHz. The NVIDIA Rubin GPU has a base clock of 700 MHz and a boost clock of 2267 MHz. The Rubin's memory clock is 2695 MHz with 10.8 Gbps effective data rate, while the Arc's memory clock is system shared.

The shading unit counts are 896 for the Arc and 28672 for the Rubin. Texture mapping units number 56 for the Arc and 896 for the Rubin. ROP counts are 28 for the Arc and 24 for the Rubin. The Arc has 7 ray tracing cores; the Rubin lists none. The Rubin has 896 tensor cores; the Arc lists none.

Pixel rate is 61.60 GPixel/s for the Arc and 54.41 GPixel/s for the Rubin. Texture rate is 123.2 GTexel/s for the Arc and 2,031.2 GTexel/s for the Rubin. FP32 performance is 3.942 TFLOPS for the Arc and 130.0 TFLOPS for the Rubin. FP16 performance is 7.885 TFLOPS for the Arc and 260.0 TFLOPS for the Rubin, both at a 2:1 ratio.

The TDP values are 35 W for the Arc and 2300 W for the Rubin. The Rubin specifies a suggested PSU of 2700 W; the Arc lists no suggested PSU. Slot width is IGP for the Arc and SXM Module for the Rubin. The bus interface is IGP for the Arc and PCIe 6.0 x16 for the Rubin.

Memory size is system shared for the Arc and 288 GB for the Rubin. Memory type is system shared for the Arc and HBM4 for the Rubin. Bus width is system shared for the Arc and 16384 bit for the Rubin. Bandwidth is system dependent for the Arc and 22.1 TB/s for the Rubin.

The process node is 5 nm for the Arc and 3 nm for the Rubin, both at TSMC. The Rubin's transistor count is 336,000 million, its die size is 1456 mm², and its transistor density is 230.8M per mm². The Arc's transistor count, die size, and density are unknown or null. The Rubin's API support is N/A across DirectX, OpenGL, and Vulkan, while the Arc supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Release dates are January 2025 for the Arc and December 2025 for the Rubin. Neither product has a launch MSRP recorded.