Nvidia N1X (40SM) vs Intel Xe3 Graphics (4-Core)
VS
Nvidia N1X (40SM)
GB20B
Intel Xe3 Graphics (4-Core)
Panther Lake
We compared two integrated laptop graphics cards: the Nvidia N1X (40SM) with 40 pipelines and 5120 shaders against the 5 months older Intel Xe3 Graphics (4-Core) that utilizes 4 pipelines and 512 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.
Please note that the tests on the Nvidia N1X (40SM) are done on an engineering sample provided by our insiders. The data will be more accurate after the final version of this GPU is available.
Key differences
Reasons to consider the Nvidia N1X (40SM)
- 10x higher maximum theoretical performance (26 vs 2.6 TFLOPS)
- Has 10x more shading units (5120 vs 512)
- Features 128 more tensor cores for effective ML and AI workloads
- Supports Nvidia DLSS 4 technology
Benchmarks
Graphics cards’ performance in recent benchmarking appsGeekBench 6 GPU Compute
GB6 Compute Score
| Background Blur | - | 57.6 img/sec |
| Face Detection | - | 29.1 img/sec |
| Horizon Detection | - | 0.79 Gpixels/sec |
| Edge Detection | - | 1.02 Gpixels/sec |
| Gaussian Blur | - | 1.02 Gpixels/sec |
| Feature Matching | - | 0.34 Gpixels/sec |
| Stereo Matching | - | 61.2 Gpixels/sec |
| Particle Physics | - | 3352.7 FPS |
| API | - | OpenCL |
Artificial Intelligence Tests
Performance in machine learning and artificial intelligence tasksGeekBench 6 ML
GB6 ML Single Precision
GB6 ML Half Precision
GB6 ML Quantized
| Image Classification (SP) | - | 4265 |
| Image Segmentation (HP) | - | 11549 |
| Image Super Resolution (Q) | - | 4466 |
| Face Detection (HP) | - | 16012 |
| Pose Estimation (Q) | - | 8425 |
| Text Classification (SP) | - | 1380 |
| Machine Translation (HP) | - | 4037 |
| Object Detection (SP) | - | 4026 |
| Depth Estimation (Q) | - | 10708 |
| Style Transfer (SP) | - | 35823 |
| Framework | - | ONNX |
| Backend | - | DirectML |
Specifications
Technical specifications of Nvidia N1X (40SM) and Intel Xe3 Graphics (4-Core)General
| Vendor | Nvidia | Intel |
| Build | Integrated | Integrated |
| Released | June 1, 2026 | January 5, 2026 |
| Case | Laptop | Laptop |
| Purpose | Professional | Generic |
| Segment | Mid-range | Entry-level |
| Architecture | Blackwell (N1x) | Celestial |
| GPU Codename | GB20B | Panther Lake |
| Rival Equivalent | - Apple M5 Max GPU (32-core) | - |
| Recommended CPU | - Nvidia RTX Spark N1X (18-Core) or above | - Intel Core Ultra 9 386H or above |
| Used in CPUs | - Nvidia RTX Spark N1X (18-Core) | - Intel Core Ultra 9 386H - Intel Core Ultra 7 366H - Intel Core Ultra 7 365 - Intel Core Ultra 7 356H - Intel Core Ultra 7 355 - Intel Core Ultra 5 336H - Intel Core Ultra 5 335 - Intel Core Ultra 5 325 |
Laptop GPU ranking (#77th place)
Graphics Processing Unit
| Base Clock | 1665 MHz | 300 MHz |
| Boost Clock | 2535 MHz | 2500 MHz |
| Shading Units | 5120 | 512 |
| Texture Mapping Units (TMUs) | 160 | 32 |
| Render Output Units (ROPs) | 40 | 16 |
| Compute Units (Pipelines) | 40 | 4 |
| Tensor Cores | 160 | 32 |
| Ray-tracing Cores | 40 | 4 |
| L1 Cache | 128KB per cluster | 64KB per cluster |
| L2 Cache | 24MB shared | 4MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 101 GPixel/s | 40 GPixel/s |
| Texture Fill Rate | 406 GTexel/s | 80 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 5.0 x16 | PCIe 5.0 |
| TGP | - | 25 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 3 nm | 3 nm |
| Die Size | 173.6 mm² | - |
| Max. Temperature | - | 100°C |
Memory
| Memory Type | System Shared | System Shared |
| ECC | No | No |
API
| DirectX | - | 12.1 |
| Vulkan | 1.4 | 1.4 |
| OpenGL | - | 4.6 |
| OpenCL | 3.0 | 3.0 |
| CUDA | 12.1 | - |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 4 | No |
| DisplayPort | - | 2.1 |
Cast your vote
Total votes: < 1