Intel Arc 140T Mobile vs NVIDIA Rubin GPU Comparison

Head-to-Head Benchmarks

The recorded data contains no direct benchmark results for either the Intel Arc 140T Mobile or the NVIDIA Rubin GPU. Both entries show an average benchmark score of 0 and zero recorded wins in head-to-head comparisons. The percentile versus all GPUs for both parts is identical at 50, indicating the database has not yet placed either product relative to the broader GPU landscape based on measured performance.

Without benchmark scores, the comparison must rely on the theoretical throughput figures listed in the database. In FP32 compute, the NVIDIA Rubin GPU delivers 130.0 TFLOPS, which is 27 times the 4.813 TFLOPS of the Intel Arc 140T Mobile. In FP16, the Rubin GPU reaches 260.0 TFLOPS, while the Intel part achieves 9.626 TFLOPS. The texture rate shows a similar gulf: the Rubin GPU processes 2,031.2 GTexel/s versus 150.4 GTexel/s for the Arc 140T. The pixel rate is the one area where the Intel part leads, with 75.20 GPixel/s against 54.41 GPixel/s for the Rubin GPU, a result of the Rubin design's smaller ROP count.

The Intel Arc 140T Mobile uses 1024 shading units, 64 texture mapping units, 32 ROPs, and 8 ray tracing cores. The NVIDIA Rubin GPU deploys 28,672 shading units, 896 texture mapping units, 24 ROPs, and 896 tensor cores. The shading unit count difference explains the FP32 performance gap, while the ROP count explains the pixel rate advantage for Intel.

Architecture Differences

The Intel Arc 140T Mobile is built on the Xe-LPG+ architecture and belongs to the Arc Graphics-M (Arrow Lake) generation. It uses the Arrow Lake-H chip and is fabricated on a 5 nm process at TSMC. The database lists its transistor count and die size as unknown. The GPU operates as an integrated graphics processor, with a base clock of 300 MHz and a boost clock of 2350 MHz. Its memory configuration is entirely system shared, meaning the memory size, type, bus width, and bandwidth are all dependent on the host system's main memory. The database records the memory bandwidth as system dependent.

The NVIDIA Rubin GPU is a fundamentally different product. It uses the GR100 chip, the Rubin architecture, and belongs to the Server Rubin (Rxx) generation. It is fabricated on a 3 nm process at TSMC, and the database records 336,000 million transistors on a 1456 mm² die, resulting in a transistor density of 230.8M per mm². The base clock is 700 MHz with a boost clock of 2267 MHz. The memory subsystem is dedicated and substantial: 288 GB of HBM4 memory on a 16384 bit bus, with a bandwidth of 22.1 TB/s. The memory clock is listed as 2695 MHz with 10.8 Gbps effective data rate.

The API support differs completely. The Intel part supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The NVIDIA Rubin GPU lists N/A for DirectX, OpenGL, and Vulkan, reflecting its server-oriented design with no display outputs. The Intel part's display outputs are portable device dependent, while the Rubin GPU has no outputs.

The form factor and power requirements are in different classes. The Intel Arc 140T is an IGP with a 35 W TDP and uses the IGP bus interface. The NVIDIA Rubin GPU is an SXM Module with a 2300 W TDP and a suggested PSU of 2700 W. It uses a PCIe 6.0 x16 bus interface.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The NVIDIA Rubin GPU delivers 130.0 TFLOPS of FP32 compute, compared to 4.813 TFLOPS for the Intel Arc 140T Mobile. The Rubin GPU is approximately 27 times faster in this metric.

Q: How do the memory systems compare?

A: The Intel Arc 140T Mobile uses system shared memory, with size, type, bus width, and bandwidth all dependent on the host system. The NVIDIA Rubin GPU has a dedicated 288 GB HBM4 memory pool on a 16384 bit bus with 22.1 TB/s of bandwidth.

Q: Which GPU has a higher pixel fill rate?

A: The Intel Arc 140T Mobile has a pixel rate of 75.20 GPixel/s, which is higher than the 54.41 GPixel/s of the NVIDIA Rubin GPU. This is due to the Intel part having 32 ROPs versus 24 ROPs on the Rubin GPU.

Q: What are the process nodes for each GPU?

A: The Intel Arc 140T Mobile is fabricated on a 5 nm process at TSMC. The NVIDIA Rubin GPU is fabricated on a 3 nm process, also at TSMC.

Q: Do both GPUs support the same graphics APIs?

A: No. The Intel Arc 140T Mobile supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The NVIDIA Rubin GPU lists N/A for DirectX, OpenGL, and Vulkan, and it has no display outputs.

Q: What is the TDP of each GPU?

A: The Intel Arc 140T Mobile has a TDP of 35 W. The NVIDIA Rubin GPU has a TDP of 2300 W with a suggested PSU of 2700 W.

Specification Differences

The two GPUs differ in nearly every recorded specification. The process node differs: 5 nm for Intel versus 3 nm for NVIDIA. The transistor count is unknown for Intel, while NVIDIA has 336,000 million transistors. The die size is unknown for Intel, while NVIDIA has 1456 mm². The transistor density is not listed for Intel, while NVIDIA has 230.8M per mm².

Clock speeds differ: Intel has a base clock of 300 MHz and boost of 2350 MHz; NVIDIA has a base of 700 MHz and boost of 2267 MHz. The memory clock for Intel is listed as system shared, while NVIDIA has 2695 MHz with 10.8 Gbps effective.

The memory configuration is completely different: Intel uses system shared memory with system dependent bandwidth; NVIDIA uses 288 GB of HBM4 with a 16384 bit bus and 22.1 TB/s bandwidth.

Compute unit counts differ: Intel has 1024 shading units, 64 TMUs, 32 ROPs, and 8 RT cores; NVIDIA has 28,672 shading units, 896 TMUs, 24 ROPs, and 896 tensor cores. Intel has no tensor cores listed; NVIDIA has no RT cores listed.

Throughput rates differ: Intel has a pixel rate of 75.20 GPixel/s and texture rate of 150.4 GTexel/s; NVIDIA has a pixel rate of 54.41 GPixel/s and texture rate of 2,031.2 GTexel/s. FP32 is 4.813 TFLOPS for Intel versus 130.0 TFLOPS for NVIDIA. FP16 is 9.626 TFLOPS for Intel versus 260.0 TFLOPS for NVIDIA.

TDP differs: 35 W for Intel versus 2300 W for NVIDIA. The slot width is IGP for Intel and SXM Module for NVIDIA. The bus interface is IGP for Intel and PCIe 6.0 x16 for NVIDIA. Display outputs are portable device dependent for Intel and no outputs for NVIDIA.

API support differs: Intel supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4; NVIDIA lists N/A for all three.

Release dates differ: Intel released on 2025-01-12, NVIDIA on 2025-12-31. The predecessor for Intel is HD Graphics-M; for NVIDIA it is Server Blackwell. Production status for both is active.

The Verdict

The data shows two products with no overlap in purpose. The Intel Arc 140T Mobile is an integrated GPU with a 35 W TDP, designed for portable devices. The NVIDIA Rubin GPU is a server module with a 2300 W TDP, a 2700 W suggested PSU, and no display outputs. The benchmark database has not recorded any measured performance for either part, so the verdict rests on the recorded specifications.

The NVIDIA Rubin GPU dominates in raw compute. Its FP32 throughput of 130.0 TFLOPS is roughly 27 times the Intel part's 4.813 TFLOPS. Its FP16 throughput of 260.0 TFLOPS is roughly 27 times the Intel part's 9.626 TFLOPS. Its texture rate of 2,031.2 GTexel/s is more than 13 times the Intel part's 150.4 GTexel/s. Its memory bandwidth of 22.1 TB/s is in a different class entirely compared to the system dependent bandwidth of the Intel part.

The Intel Arc 140T Mobile wins only in pixel rate, with 75.20 GPixel/s versus 54.41 GPixel/s for the Rubin GPU. It also has a lower TDP by a wide margin, 35 W versus 2300 W, and supports standard graphics APIs that the Rubin GPU lacks.

For a portable device requiring integrated graphics with API support and low power draw, the Intel part is the only option that fits. For server compute workloads requiring massive FP32 and FP16 throughput, large memory capacity, and tensor core acceleration, the NVIDIA Rubin GPU is the clear choice. The data does not support any crossover between these roles.

Where Each One Wins

The Intel Arc 140T Mobile wins in pixel fill rate. At 75.20 GPixel/s, it exceeds the NVIDIA Rubin GPU's 54.41 GPixel/s. The Intel part also wins in power efficiency by a massive margin, with a 35 W TDP versus 2300 W. It supports DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4, while the Rubin GPU supports none of these APIs. The Intel part has display outputs, while the Rubin GPU has none. For integrated graphics in portable devices, the Intel part is the only viable option in this comparison.

The NVIDIA Rubin GPU wins in every compute throughput metric. FP32 is 130.0 TFLOPS versus 4.813 TFLOPS. FP16 is 260.0 TFLOPS versus 9.626 TFLOPS. Texture rate is 2,031.2 GTexel/s versus 150.4 GTexel/s. It has far more shading units, 28,672 versus 1024. It has 896 tensor cores, while the Intel part has none listed. It has 288 GB of HBM4 memory with 22.1 TB/s bandwidth, compared to the system shared memory of the Intel part. It has a larger process node advantage at 3 nm versus 5 nm, and it carries 336,000 million transistors on a 1456 mm² die.

The use case split is sharp. For rendering to a display in a portable device with low power consumption and standard graphics API support, the Intel Arc 140T Mobile is the appropriate choice. For server workloads requiring extreme compute throughput, tensor core acceleration, and high-capacity HBM4 memory, the NVIDIA Rubin GPU is the only part that matches those requirements. The data shows no scenario where both parts compete for the same task.