Intel Arc 130T Mobile vs NVIDIA GeForce RTX 5090 SE Comparison

The Verdict

The database comparison between the Intel Arc 130T Mobile and the NVIDIA GeForce RTX 5090 SE is a study in extreme contrast. The Arc 130T is an integrated graphics processor (IGP) designed for thin, power-lean laptops, while the RTX 5090 SE is a flagship, dual-slot discrete desktop card. Benchmark results, where available, show a massive performance gulf, but the recorded data indicates the two products target entirely different use cases. The RTX 5090 SE is the clear choice for maximum compute and frame rates, while the Arc 130T is suited for portable, low-power systems where a discrete GPU cannot fit. The RTX 5090 SE delivers over 16 times the FP32 throughput, has a 24 GB GDDR7 frame buffer, and consumes 500 W, while the Arc 130T uses 35 W and shares system memory. The data confirms that no user would choose between these two for the same task; the decision is dictated entirely by platform constraints.

Architecture Differences

The architectural split between the Intel Arc 130T Mobile and the NVIDIA GeForce RTX 5090 SE is fundamental. The Intel part is built on the Xe-LPG+ architecture, part of the Arrow Lake-H chip, and uses a 5 nm process from TSMC. It is an integrated GPU with a 300 MHz base clock and a 2200 MHz boost clock. The NVIDIA part uses the Blackwell 2.0 architecture on the GB202 chip, also fabricated on a 5 nm TSMC process, but it is a discrete accelerator with a 1740 MHz base and 2377 MHz boost clock. The Arc 130T is the predecessor to HD Graphics-M, while the RTX 5090 SE is the successor to GeForce 40 and has a successor in GeForce 60.

The RTX 5090 SE has 92,200 million transistors on a 750 mm² die, with a transistor density of 122.9M per mm². The Intel part's transistor count and die size are not recorded in the database. The NVIDIA GPU includes 14,080 shading units, 440 texture mapping units, 160 ROPs, 110 RT cores, and 440 tensor cores. The Intel GPU has 896 shading units, 56 TMUs, 28 ROPs, and 7 RT cores, with no tensor core count listed. The FP32 throughput for the RTX 5090 SE is 66.94 TFLOPS, and FP16 is also 66.94 TFLOPS with a 1:1 ratio. The Arc 130T delivers 3.942 TFLOPS FP32 and 7.885 TFLOPS FP16 with a 2:1 ratio. The RTX 5090 SE has a pixel rate of 380.3 GPixel/s and a texture rate of 1,045.9 GTexel/s, while the Arc 130T has 61.60 GPixel/s and 123.2 GTexel/s.

Memory architecture differs completely. The RTX 5090 SE uses 24 GB of GDDR7 on a 384 bit bus, delivering 1.34 TB/s bandwidth. The Arc 130T uses system shared memory, with a system dependent bandwidth and no dedicated VRAM. The NVIDIA card runs memory at 1750 MHz, 28 Gbps effective, while the Intel IGP has no dedicated memory clock. The RTX 5090 SE uses a PCIe 5.0 x16 interface, whereas the Arc 130T is integrated with an IGP bus interface. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The NVIDIA GeForce RTX 5090 SE records 66.94 TFLOPS FP32, compared to the Intel Arc 130T Mobile's 3.942 TFLOPS. The NVIDIA part is about 17 times higher in raw single-precision throughput.

Q: What are the memory configurations of the two GPUs?

A: The RTX 5090 SE has 24 GB of GDDR7 on a 384 bit bus with 1.34 TB/s bandwidth. The Arc 130T uses system shared memory with system dependent bandwidth, meaning it has no dedicated VRAM.

Q: How do the power requirements differ?

A: The RTX 5090 SE has a TDP of 500 W and requires a 900 W suggested PSU with a single 16-pin connector. The Arc 130T has a TDP of 35 W and no power connectors listed, as it is an IGP.

Q: What is the physical form factor of each product?

A: The RTX 5090 SE is a dual-slot card measuring 267 mm in length, 111 mm in height, and 40 mm in width. The Arc 130T is an IGP with no slot width, meaning it is integrated into the motherboard.

Q: Which GPU has more RT cores and tensor cores?

A: The RTX 5090 SE has 110 RT cores and 440 tensor cores. The Arc 130T has 7 RT cores and no tensor core count is recorded in the database.

Q: What are the release dates for these products?

A: The Intel Arc 130T Mobile was released on 2025-01-12, and the NVIDIA GeForce RTX 5090 SE has a release date of 2025-12-31.

Specification Differences

The following fields show direct differences between the Intel Arc 130T Mobile and the NVIDIA GeForce RTX 5090 SE.

• Architecture: Xe-LPG+ vs Blackwell 2.0
• Chip: Arrow Lake-H vs GB202
• Generation: Arc Graphics-M (Arrow Lake) vs GeForce 50
• Transistors: unknown vs 92,200 million
• Die Size: unknown vs 750 mm²
• Transistor Density: not listed vs 122.9M / mm²
• Base Clock: 300 MHz vs 1740 MHz
• Boost Clock: 2200 MHz vs 2377 MHz
• Memory Clock: System Shared vs 1750 MHz 28 Gbps effective
• Memory Size: System Shared vs 24 GB
• Memory Type: System Shared vs GDDR7
• Memory Bus Width: System Shared vs 384 bit
• Memory Bandwidth: System Dependent vs 1.34 TB/s
• Shading Units: 896 vs 14080
• TMUs: 56 vs 440
• ROPs: 28 vs 160
• RT Cores: 7 vs 110
• Tensor Cores: not listed vs 440
• Pixel Rate: 61.60 GPixel/s vs 380.3 GPixel/s
• Texture Rate: 123.2 GTexel/s vs 1,045.9 GTexel/s
• FP32: 3.942 TFLOPS vs 66.94 TFLOPS
• FP16: 7.885 TFLOPS (2:1) vs 66.94 TFLOPS (1:1)
• TDP: 35 W vs 500 W
• Slot Width: IGP vs Dual-slot
• Power Connectors: none listed vs 1x 16-pin
• Suggested PSU: none vs 900 W
• Bus Interface: IGP vs PCIe 5.0 x16
• Display Outputs: Portable Device Dependent vs 1x HDMI 2.1b3x DisplayPort 2.1b
• Dimensions: not listed vs 267 mm 10.5 inches length, 111 mm 4.4 inches height, 40 mm 1.6 inches width
• Release Date: 2025-01-12 vs 2025-12-31
• Predecessor: HD Graphics-M vs GeForce 40
• Successor: none vs GeForce 60
• Launch MSRP: none vs 1,499 USD

Head-to-Head Benchmarks

The head-to-head benchmark data set is empty in the database, so no direct run-to-run comparisons are recorded. However, the specification sheet provides clear quantitative deltas that serve as a proxy for expected performance. The most significant advantage for the NVIDIA GeForce RTX 5090 SE is in raw compute. The data shows 66.94 TFLOPS FP32 for the RTX 5090 SE versus 3.942 TFLOPS for the Intel Arc 130T Mobile, which is a 16.98 times difference. FP16 performance is similarly lopsided: the RTX 5090 SE delivers 66.94 TFLOPS, while the Arc 130T delivers 7.885 TFLOPS, meaning the NVIDIA part is about 8.5 times higher in half-precision throughput.

Memory bandwidth is another decisive win. The RTX 5090 SE has 1.34 TB/s of dedicated bandwidth, while the Arc 130T is system dependent. In practical terms, the discrete card's 24 GB GDDR7 frame buffer at 384 bit width allows for large texture sets and high-resolution rendering, whereas the Intel IGP must compete with the CPU for system memory. Pixel throughput favors the NVIDIA card at 380.3 GPixel/s versus 61.60 GPixel/s, and texture rate is 1,045.9 GTexel/s versus 123.2 GTexel/s. Each of these ratios, 6.17 times for pixel rate and 8.49 times for texture rate, indicates that the RTX 5090 SE will dominate fill-rate-bound workloads.

Clock speeds also show a gap. The RTX 5090 SE boosts to 2377 MHz, which is 177 MHz higher than the Arc 130T's 2200 MHz boost. Base clocks differ more substantially, at 1740 MHz versus 300 MHz, but the Intel part is an integrated chip with a low-power design. The RTX 5090 SE has 110 RT cores against 7, and 440 tensor cores against none listed. This suggests the NVIDIA card has a major advantage in ray tracing and AI-accelerated workloads, though no benchmark scores are recorded to quantify the real-world impact.

The only area where the Intel Arc 130T Mobile holds an advantage is power consumption. Its 35 W TDP is dramatically lower than the RTX 5090 SE's 500 W. The Arc 130T also uses no dedicated power connector and has no recommended PSU, while the RTX 5090 SE requires a 900 W power supply. The Intel part is an IGP with a portable device dependent display output, meaning it can fit into ultra-thin systems without a discrete card. The RTX 5090 SE is a dual-slot card with a length of 267 mm and a height of 111 mm, which requires a full desktop chassis.

Both GPUs share the same API support, including DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. This means software compatibility is similar, but the performance envelope is not. The NVIDIA card's architecture, Blackwell 2.0, is built on the same 5 nm TSMC process as the Intel part's Xe-LPG+, but the sheer scale of the GB202 chip, with 92,200 million transistors versus an unknown count for Arrow Lake-H, accounts for the massive compute difference.

In terms of release cadence, the Arc 130T launched on 2025-01-12, and the RTX 5090 SE is dated 2025-12-31. The NVIDIA card carries a launch MSRP of 1,499 USD, while the Intel part has no recorded MSRP, consistent with its integrated nature. The data does not include any benchmark scores or percentile rankings beyond a neutral 50th percentile for both, so the evaluation rests entirely on the specification deltas. The verdict from the recorded data is unambiguous: the RTX 5090 SE is a high-end discrete accelerator with orders-of-magnitude higher throughput, and the Arc 130T is a low-power integrated solution. The RTX 5090 SE wins every performance metric except power draw and physical integration.