Quick/Comparisons
16 | Gaming | 29 |
25 | Workstation | 34 |
22 | AI/ML |
Compare with something else?
Compare Intel Arc B390 with another →26 |
100 | Energy Efficiency | 50 |
33 | Quick Comparison Final Score | 34 |
| Panther Lake | Graphics Processor | Navi 22 |
| 1536 | Cores | 2304 |
| 48 / 24 | TMUs / ROPs | 144 / 64 |
| 1268.79 | Blender GPU | 1185.54 |
| 38 | Forza Horizon 5 | 74 |
| 55 | The Witcher 3 | 95 |
| 60 | Counter-Strike 2 | 131 |
| 49 | Far Cry 6 | 90 |
| 21 | Hogwarts Legacy | 56 |
| 32 | Call of Duty | 86 |
| 25 | Ghost of Tsushima | 57 |
| 33 | Cyberpunk 2077 | 63 |
| 52 | Tomb Raider | 105 |
| 41 | Average FPS | 84 |
| 52 | 1080p High | 106 |
| 41 | 1080p Ultra | 84 |
| 29 | 1440p Ultra | 58 |
| 14 | 4K Ultra | 32 |
| Low | Margin of Error | High |
| 64546 | GB6 Compute Score | 92153 |
| — | Background Blur | 209.2 img/sec |
| — | Face Detection | 115.4 img/sec |
| — | Horizon Detection | 3.3 Gpixels/sec |
| — | Edge Detection | 4.7 Gpixels/sec |
| — | Gaussian Blur | 3.81 Gpixels/sec |
| — | Feature Matching | 0.94 Gpixels/sec |
| — | Stereo Matching | 327.1 Gpixels/sec |
| — | Particle Physics | 13207.5 FPS |
| — | API | OpenCL |
| 9029 | G3D Mark Score | 13617 |
| 786 | G2D Mark | 554 |
| 70 FPS | DirectX 11 | 129 FPS |
| 50 FPS | DirectX 12 | 65 FPS |
| 3702 Ops/s | GPU Compute | 5188 Ops/s |
| 11871 | GB6 ML Single Precision | 14369 |
| 20120 | GB6 ML Half Precision | 15396 |
| 7879 | GB6 ML Quantized | 12333 |
| 5487 | Image Classification (SP) | 5874 |
| 16864 | Image Segmentation (HP) | 8129 |
| 8788 | Image Super Resolution (Q) | 18554 |
| 25029 | Face Detection (HP) | 18625 |
| 18852 | Pose Estimation (Q) | 84252 |
| 2115 | Text Classification (SP) | 1089 |
| 4266 | Machine Translation (HP) | 3605 |
| 7449 | Object Detection (SP) | 7294 |
| 22207 | Depth Estimation (Q) | 31037 |
| 95039 | Style Transfer (SP) | 154983 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 60 GPixel/s | Pixel Fill Rate | 110-147 GPixel/s |
| 120 GTexel/s | Texture Fill Rate | 248-331 GTexel/s |
| 7.7 TFLOPS | FLOPS (FP32) | 7.9-10.6 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 10 GB |
| — | Memory Clock | 1750 MHz |
| — | Effective Memory Speed | 14000 Mbps |
| — | Bus | 160-bit |
| No | ECC | No |
| — | Memory Bandwidth | 280 GB/s |
| PCIe 5.0 | Interface | PCIe 4.0 x16 |
| — | TGP | 80-135 W (configurable) |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 7 nm |
| — | Die Size | 335 mm² |
| — | Transistor Count | 17.2 billion |
| — | Transistor Density | 51.34 MTr/mm² |
| 12.1 | DirectX | 12 |
| 1.4 | Vulkan | 1.2 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.1 |
| — | CUDA | — |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| 2.1 | DisplayPort | 1.4 |
| Intel | Vendor | Amd |
| Integrated | Build | Discrete |
| January 5, 2026 | Released | June 1, 2021 |
| Laptop | Case | Laptop |
| Gaming | Purpose | Gaming |
| Mid-range | Segment | High-end |
| Celestial | Architecture | RDNA 2.0 |
| Panther Lake | GPU Codename | Navi 22 |
| -Intel Core Ultra X9 388Hor above | Recommended CPU | -AMD Ryzen 7 5800Hor above |
| 4242 | Steel Nomad Lite Score | 8784 |
| 6595 | Time Spy | 9496 |
| 26399 | Solar Bay | 37680 |
| 3886 | Port Royal | 4554 |
| 16770 | Fire Strike | 27957 |
| 11707 | Wild Life Extreme | 17363 |
| 68498 | Night Raid | 72638 |
| 300 MHz | Base Clock | 1489 MHz |
| 2500 MHz | Boost Clock | 1720-2300 MHz (configurable) |
| 1536 | Shading Units | 2304 |
| 48 | Texture Mapping Units (TMUs) | 144 |
| 24 | Render Output Units (ROPs) | 64 |
| 12 | Compute Units (Pipelines) | 36 |
| — | Tensor Cores | — |
| — | Ray-tracing Cores | 36 |
| 64KB per cluster | L1 Cache | 128KB per cluster |
| 16MB shared | L2 Cache | 3MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |