Intel Iris Xe Graphics 80EU Mobile vs NVIDIA N1 20SM Comparison

Head-to-Head Benchmarks

The recorded database contains no head-to-head benchmark entries for these two mobile graphics parts, and neither unit has accumulated an average benchmark score. This absence of measured data is itself informative: the Intel Iris Xe Graphics 80EU Mobile and the NVIDIA N1 20SM sit at the same 50th percentile versus all GPUs in the database, which places them in a statistical tie despite their very different underlying designs. With zero wins recorded for either side, the comparison must be built entirely from the architectural specifications and the theoretical throughput figures each vendor has published.

The raw computational ceiling strongly favors the NVIDIA part. The N1 20SM delivers 12.01 TFLOPS of FP32 performance, which is roughly 6.5 times the 1.856 TFLOPS offered by the Intel Iris Xe. In FP16 compute, the gap narrows slightly in relative terms but remains vast in absolute numbers: the N1 outputs 12.01 TFLOPS in a 1:1 ratio, while the Iris Xe reaches 3.712 TFLOPS using a 2:1 rate. This means the NVIDIA chip can process heavy FP16 workloads such as AI inference and certain rendering passes at more than three times the rate of the Intel part.

Texture throughput tells a similar story. The N1 20SM achieves 375.4 GTexel/s, while the Iris Xe manages only 58.00 GTexel/s. That is a 6.5-fold advantage for NVIDIA in texture-heavy scenes, which translates directly to faster filtering of detailed surfaces in modern game engines. Pixel throughput is closer but still clearly favors NVIDIA: 56.30 GPixel/s versus 29.00 GPixel/s, a 1.94x lead. The Intel part does hold its own on raw clock speed in one respect, its 1450 MHz boost clock is higher than the N1's 2346 MHz boost, but the NVIDIA chip compensates with 2560 shading units against Intel's 640, exactly four times the shader count.

Memory bandwidth is another decisive separation. The N1 20SM uses a 256-bit LPDDR5X bus rated at 273.2 GB/s, while the Iris Xe relies on system-shared memory with bandwidth described as "System Dependent." The Intel part offers no dedicated bandwidth figure, which means its real-world memory throughput depends entirely on the host platform's DRAM configuration. The NVIDIA part, by contrast, has a fixed 128 GB capacity with a guaranteed 273.2 GB/s pipeline, a configuration that removes a major variable from performance prediction.

Architecture Differences

The two GPUs come from fundamentally different design lineages. The Intel Iris Xe Graphics 80EU Mobile is built on Generation 12.2 architecture, specifically the HD Graphics-M variant of Raptor Lake. It uses a 10 nm process node manufactured by Intel itself. The NVIDIA N1 20SM is a Blackwell 2.0 design, part of the Blackwell IGP (N1x) generation, fabricated on a 5 nm node at TSMC. The process difference alone explains part of the efficiency and density gap, though the database does not list transistor counts for either part.

The NVIDIA chip is physically large for an integrated GPU, with a die size of 382 mm². The Intel part has no die size listed, but as a Raptor Lake IGP it shares the CPU package rather than existing as a standalone die. The N1's dedicated die size suggests it was designed as a serious compute unit in its own right, not merely as a supplemental graphics block. The NVIDIA part also carries hardware features that the Intel IGP lacks entirely: 20 ray tracing cores and 80 tensor cores. The Intel Iris Xe has neither. This is a structural difference, not a clock or core count nuance. Ray tracing acceleration and tensor-based AI workloads are simply absent from the Intel architecture.

Memory architecture reinforces the divide. The N1 20SM has its own 128 GB LPDDR5X pool on a 256-bit bus, while the Iris Xe shares system memory with no dedicated bus width or capacity. The N1's memory clock is listed at 1067 MHz with 8.5 Gbps effective data rate. The Intel part's memory clock is listed simply as "System Shared," indicating no fixed memory clock of its own. The NVIDIA part connects via PCIe 5.0 x16, while the Intel IGP uses a Ring Bus interface, which ties it directly to the CPU's internal fabric rather than an external expansion bus.

API support also separates the two. The Intel Iris Xe supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The NVIDIA N1 20SM lists DirectX as "N/A," OpenGL as "N/A," and Vulkan as "N/A." This is a striking difference: the NVIDIA part appears to offer no conventional graphics API compatibility in the recorded data, which suggests its primary role may be compute-oriented rather than traditional gaming graphics. The Intel part, by contrast, is fully equipped for standard graphics workloads across all major APIs.

Where Each One Wins

The Intel Iris Xe Graphics 80EU Mobile wins in scenarios where software compatibility and conventional graphics rendering matter. Its DirectX 12_1 support, OpenGL 4.6, and Vulkan 1.4 coverage mean it can run the broadest range of existing PC games and graphics applications without translation layers or compatibility shims. Its 15 W TDP, while not a performance figure, indicates a power envelope suited to thin-and-light laptops where the entire platform must stay within tight thermal limits. The Iris Xe also carries a production status of "Active" with a release date in January 2023, meaning it is a current, supported part for mainstream mobile systems.

The NVIDIA N1 20SM wins decisively in raw compute throughput. Its 12.01 TFLOPS FP32 and FP16 performance, combined with 375.4 GTexel/s texture rate and 56.30 GPixel/s pixel rate, place it in a different performance class entirely. The presence of 20 ray tracing cores and 80 tensor cores gives it dedicated hardware for ray-traced lighting and AI-accelerated workloads, neither of which the Intel part can accelerate in hardware. The 273.2 GB/s memory bandwidth and 128 GB capacity make it suitable for large datasets that would overwhelm the system-shared memory approach of the Iris Xe. The NVIDIA part is also newer, with a release date in May 2026, and it uses a more advanced 5 nm TSMC process.

For gaming specifically, the Intel part has the API compatibility advantage, but the NVIDIA part has the raw fill rates. Without benchmark data, the practical gaming outcome is uncertain, though the sheer compute and texture advantage of the N1 suggests it would outperform in any workload that does not require DirectX or Vulkan. For compute tasks such as machine learning inference, physics simulation, or video processing, the N1's tensor cores and FP16 capability give it a structural lead that the Iris Xe cannot match.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The NVIDIA N1 20SM delivers 12.01 TFLOPS of FP32 performance, while the Intel Iris Xe Graphics 80EU Mobile provides 1.856 TFLOPS. The NVIDIA part is approximately 6.5 times faster in FP32 workloads.

Q: Does the Intel Iris Xe support ray tracing?

A: No. The Intel Iris Xe Graphics 80EU Mobile has no ray tracing cores listed in the database. The NVIDIA N1 20SM includes 20 ray tracing cores.

Q: What memory configuration does each GPU use?

A: The Intel Iris Xe uses system-shared memory with no dedicated capacity, bus width, or bandwidth figure; its bandwidth is listed as "System Dependent." The NVIDIA N1 20SM has 128 GB of LPDDR5X memory on a 256-bit bus with 273.2 GB/s bandwidth.

Q: Which GPU supports DirectX 12?

A: The Intel Iris Xe supports DirectX 12 (12_1), along with OpenGL 4.6 and Vulkan 1.4. The NVIDIA N1 20SM lists DirectX, OpenGL, and Vulkan all as "N/A" in the database.

Q: What are the process nodes for these two chips?

A: The Intel Iris Xe is fabricated on a 10 nm process at Intel. The NVIDIA N1 20SM uses a 5 nm process at TSMC.

Q: How many shading units does each GPU have?

A: The Intel Iris Xe has 640 shading units, while the NVIDIA N1 20SM has 2560 shading units, exactly four times as many.

Specification Differences

The two GPUs differ across nearly every measurable specification. The Intel Iris Xe Graphics 80EU Mobile uses the Raptor Lake chip with Generation 12.2 architecture, while the NVIDIA N1 20SM uses the GB20B chip with Blackwell 2.0 architecture. Process nodes are 10 nm (Intel) versus 5 nm (TSMC). The NVIDIA part has a die size of 382 mm²; the Intel part has none listed. Base clocks are 300 MHz for Intel and 741 MHz for NVIDIA. Boost clocks are 1450 MHz for Intel and 2346 MHz for NVIDIA. Memory is system-shared for Intel versus 128 GB LPDDR5X for NVIDIA. Bus width is system-shared for Intel versus 256 bit for NVIDIA. Bandwidth is system-dependent for Intel versus 273.2 GB/s for NVIDIA.

Shading units are 640 versus 2560. TMUs are 40 versus 160. ROPs are 20 versus 24. Ray tracing cores are absent on Intel and 20 on NVIDIA. Tensor cores are absent on Intel and 80 on NVIDIA. Pixel rate is 29.00 GPixel/s versus 56.30 GPixel/s. Texture rate is 58.00 GTexel/s versus 375.4 GTexel/s. FP32 is 1.856 TFLOPS versus 12.01 TFLOPS. FP16 is 3.712 TFLOPS (2:1) versus 12.01 TFLOPS (1:1). TDP is 15 W for Intel and unknown for NVIDIA. Bus interface is Ring Bus for Intel and PCIe 5.0 x16 for NVIDIA. Display outputs are portable-device-dependent for Intel and 1x HDMI for NVIDIA.

API support is the starkest difference: Intel lists DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4, while NVIDIA lists "N/A" for all three. Release dates are January 2023 for Intel and May 2026 for NVIDIA. The Intel part has a successor listed as Arc Graphics-M; the NVIDIA part has no successor. Power connectors are absent on both, and neither has a launch MSRP in the database.

The Verdict

The data points to two different devices serving different purposes. The Intel Iris Xe Graphics 80EU Mobile is a conventional integrated GPU aimed at standard graphics workloads on mainstream laptops. Its DirectX 12_1, OpenGL 4.6, and Vulkan 1.4 support make it a drop-in solution for existing software, and its 15 W TDP fits thin chassis designs. Its performance ceiling is modest, with 1.856 TFLOPS FP32 and 58.00 GTexel/s texture rate, but it is a complete graphics solution for everyday use.

The NVIDIA N1 20SM is a different class of hardware. Its 12.01 TFLOPS FP32, 375.4 GTexel/s texture rate, and dedicated ray tracing and tensor cores indicate a compute-first design. The absence of conventional graphics API support in the database suggests it may target specialized compute environments rather than general-purpose gaming. Its 128 GB memory capacity and 273.2 GB/s bandwidth point to data-heavy workloads such as AI training, scientific computing, or large-scale rendering tasks that do not rely on DirectX or Vulkan.

For users running standard PC games or graphics applications, the Intel part has the compatibility advantage and a clear power envelope. For users needing raw compute throughput, tensor acceleration, or ray tracing hardware, the NVIDIA part is the only choice between these two. The 50th percentile ranking for both parts in the database reflects their median position across all GPUs, but the underlying specifications show they achieve that ranking through entirely different means. The Intel part wins on software reach and integration simplicity. The NVIDIA part wins on sheer computational power and specialized hardware features.