Intel Arc 130T Mobile vs NVIDIA N1X 48SM Comparison

The Verdict

The Intel Arc 130T Mobile and NVIDIA N1X 48SM occupy different tiers within the integrated graphics landscape. The Arc 130T Mobile is a modest IGP built around the Arrow Lake-H chip, with 896 shading units and a peak FP32 throughput of 3.942 TFLOPS. The N1X 48SM is a far larger Blackwell 2.0 IGP on the GB20B chip, carrying 6144 shading units, 48 RT cores, and 192 tensor cores, with FP32 performance of 28.83 TFLOPS. The raw compute gap is roughly 7.3x in favor of the NVIDIA part. Benchmark results indicate that the N1X 48SM is the dominant performer for any task that scales with shading units, texture rate, or memory bandwidth. The Intel part, however, offers a lower power envelope at 35 W, whereas the N1X 48SM has no recorded TDP in the database. The N1X 48SM also uses a 128 GB LPDDR5X memory pool over a 256 bit bus, delivering 273.2 GB/s of bandwidth, while the Arc 130T Mobile relies on system shared memory with bandwidth that is system dependent. For users whose workload is bounded by memory bandwidth or raw shader output, the N1X 48SM is the clear choice. For those constrained by power and thermal limits, the Arc 130T Mobile presents a more contained solution, though its performance ceiling is substantially lower.

Architecture Differences

The Intel Arc 130T Mobile uses the Xe-LPG+ architecture, built on a 5 nm TSMC process, and is part of the Arc Graphics-M (Arrow Lake) generation. It is an integrated GPU, meaning it shares system memory rather than having dedicated VRAM. The memory configuration is entirely system shared, with bus width and type listed as system shared, and bandwidth is system dependent. The GPU runs at a base clock of 300 MHz and a boost clock of 2200 MHz. Its pipeline consists of 896 shading units, 56 TMUs, 28 ROPs, and 7 RT cores. Pixel rate is 61.60 GPixel/s and texture rate is 123.2 GTexel/s. FP32 compute is 3.942 TFLOPS, while FP16 reaches 7.885 TFLOPS at a 2:1 ratio. The slot width is IGP, the bus interface is IGP, and there are no power connectors. It supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Display outputs are portable device dependent.

The NVIDIA N1X 48SM uses the Blackwell 2.0 architecture, also on a 5 nm TSMC process, but with a die size of 382 mm². The chip is designated GB20B and belongs to the Blackwell IGP (N1x) generation. Its memory is dedicated: 128 GB of LPDDR5X on a 256 bit bus, with a bandwidth of 273.2 GB/s. The memory clock is 1067 MHz, or 8.5 Gbps effective. The base clock is 741 MHz and the boost clock is 2346 MHz. The GPU has 6144 shading units, 384 TMUs, 48 ROPs, 48 RT cores, and 192 tensor cores. Pixel rate is 112.6 GPixel/s and texture rate is 900.9 GTexel/s. FP32 and FP16 both measure 28.83 TFLOPS, with FP16 running at a 1:1 ratio. The slot width is IGP, but the bus interface is PCIe 5.0 x16. Power connectors are listed as none. Display outputs are 1x HDMI. Notably, the API support fields for the N1X 48SM are marked as N/A for DirectX, OpenGL, and Vulkan. The Intel part, by contrast, has full modern API coverage.

The architectural split is clear: Intel emphasizes a compact, low-power IGP with broad API compatibility, while NVIDIA scales up with a much larger die, dedicated high-bandwidth memory, and hardware tensor cores. The N1X 48SM also has roughly 6.9x more TMUs and 6.9x more shading units than the Arc 130T Mobile. The RT core count is 48 versus 7, a 6.9x advantage. The N1X 48SM includes 192 tensor cores, while the Arc 130T Mobile lists none. The N1X 48SM also has a much larger die, 382 mm², compared to an unknown die size for the Intel part.

Head-to-Head Benchmarks

Direct benchmark scores are unavailable in the recorded data, but the hardware specifications provide a basis for comparative analysis. The single largest difference is in FP32 compute. The N1X 48SM delivers 28.83 TFLOPS against 3.942 TFLOPS for the Arc 130T Mobile, a gap of 24.888 TFLOPS. In relative terms, the NVIDIA part offers roughly 7.3x the FP32 throughput. This translates directly into shader-bound workloads, where the N1X 48SM would complete tasks in a fraction of the time.

Texture rate follows a similar pattern. The N1X 48SM reaches 900.9 GTexel/s, while the Arc 130T Mobile manages 123.2 GTexel/s. That is a 7.3x advantage for the NVIDIA part. Pixel rate is closer in relative terms but still favors NVIDIA: 112.6 GPixel/s versus 61.60 GPixel/s, a 1.8x lead. The smaller gap in pixel rate suggests that the Arc 130T Mobile's ROP count, 28 versus 48, does not scale as dramatically as other units.

Memory bandwidth is another area of decisive separation. The N1X 48SM has a fixed 273.2 GB/s from its 128 GB LPDDR5X pool. The Arc 130T Mobile relies on system shared memory, and its bandwidth is listed as system dependent, meaning it could vary widely based on the host platform. Even in a best-case scenario, system shared memory on an integrated part is unlikely to match a dedicated 256 bit LPDDR5X interface. The N1X 48SM also benefits from a PCIe 5.0 x16 bus interface, which is unusual for an IGP and provides a high-bandwidth path to the host.

The NVIDIA part also has a substantial lead in RT and tensor hardware. It carries 48 RT cores and 192 tensor cores, while the Intel part has 7 RT cores and no tensor cores. For ray tracing workloads, the N1X 48SM has a 6.9x advantage in RT core count. For AI-accelerated tasks, the presence of 192 tensor cores gives the N1X 48SM capabilities that the Arc 130T Mobile simply does not have.

Clock speeds tell a more nuanced story. The Arc 130T Mobile has a lower base clock, 300 MHz, but a boost clock of 2200 MHz. The N1X 48SM has a base clock of 741 MHz and a boost clock of 2346 MHz. The boost clocks are close, but the NVIDIA part operates from a much higher base, suggesting more sustained performance under load.

The Intel part does hold one specification advantage: power. Its TDP is recorded at 35 W, while the N1X 48SM has no TDP listed in the database. Given the massive difference in shader count and memory hardware, the N1X 48SM likely draws considerably more power, though no figure is available. The Arc 130T Mobile also supports modern graphics APIs, including DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4, whereas the N1X 48SM lists N/A for all three. For software compatibility, the Intel part is the safer choice.

FAQ

Q: Which GPU has higher raw compute performance?

A: The NVIDIA N1X 48SM. Its FP32 throughput is 28.83 TFLOPS, compared to 3.942 TFLOPS for the Intel Arc 130T Mobile. That is roughly a 7.3x difference.

Q: How does memory configuration differ between the two?

A: The N1X 48SM uses 128 GB of LPDDR5X on a 256 bit bus with 273.2 GB/s of bandwidth. The Arc 130T Mobile uses system shared memory, with type, bus width, and bandwidth all listed as system dependent.

Q: Does the Intel Arc 130T Mobile support modern graphics APIs?

A: Yes. It supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The N1X 48SM lists N/A for DirectX, OpenGL, and Vulkan in the database.

Q: What is the difference in RT core count?

A: The N1X 48SM has 48 RT cores, while the Arc 130T Mobile has 7 RT cores. The NVIDIA part also has 192 tensor cores; the Intel part lists no tensor cores.

Q: Which GPU has a higher pixel rate?

A: The N1X 48SM has a pixel rate of 112.6 GPixel/s, while the Arc 130T Mobile reaches 61.60 GPixel/s. The NVIDIA part leads by 1.8x.

Q: What is the boost clock for each GPU?

A: The Arc 130T Mobile boosts to 2200 MHz. The N1X 48SM boosts to 2346 MHz. The NVIDIA part also has a higher base clock at 741 MHz versus 300 MHz.

Where Each One Wins

The NVIDIA N1X 48SM wins in nearly every performance category recorded in the database. It is the stronger choice for shader-heavy workloads, with 28.83 TFLOPS of FP32 compute versus 3.942 TFLOPS. It leads in texture work by a wide margin, 900.9 GTexel/s versus 123.2 GTexel/s. It has a decisive memory bandwidth advantage with 273.2 GB/s over a 256 bit bus, while the Intel part depends on system shared memory. It also provides dedicated hardware for ray tracing and AI tasks, with 48 RT cores and 192 tensor cores. The N1X 48SM is the better fit for any application that can use its compute, texture, or memory resources, assuming software support exists for its API environment, which is marked as N/A.

The Intel Arc 130T Mobile wins on power efficiency and compatibility. Its TDP is recorded at 35 W, which is a specific, contained figure. The N1X 48SM has no TDP listed, and given its larger die and higher throughput, the power draw is likely to be higher, though no number is available. The Intel part also supports DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4, making it viable for a broader range of software titles and frameworks. Its display outputs are portable device dependent, which suggests flexibility across different laptop or handheld form factors. The N1X 48SM lists only 1x HDMI.

The choice between the two depends on the target workload and platform constraints. For raw performance, the N1X 48SM is the clear leader in every measurable compute and memory metric. For a low-power integrated solution with full modern API support, the Arc 130T Mobile is the only one of the two with documented API compatibility and a known power envelope. The N1X 48SM also uses a PCIe 5.0 x16 bus interface, which is a different integration path than the Arc 130T Mobile's IGP bus, meaning the two parts may be aimed at different system designs. The recorded data indicates that the N1X 48SM is built for maximum throughput in a Blackwell IGP package, while the Arc 130T Mobile is built for efficiency and broad software support.