Quick/Comparisons
16 | Gaming | 64 |
25 | Workstation | 60 |
22 | AI/ML |
Compare with something else?
Compare Intel Arc B390 with another →59 |
100 | Energy Efficiency | 44 |
33 | Quick Comparison Final Score | 62 |
| Panther Lake | Graphics Processor | Navi 31 |
| 1536 | Cores | 5120 |
| 48 / 24 | TMUs / ROPs | 320 / 160 |
| 1268.79 | Blender GPU | 2808.96 |
| 38 | Forza Horizon 5 | 143 |
| 55 | The Witcher 3 | 201 |
| 60 | Counter-Strike 2 | 217 |
| 49 | Far Cry 6 | 155 |
| 21 | Hogwarts Legacy | 109 |
| 32 | Call of Duty | 190 |
| 25 | Ghost of Tsushima | 116 |
| 33 | Cyberpunk 2077 | 138 |
| 52 | Tomb Raider | 221 |
| 41 | Average FPS | 166 |
| 52 | 1080p High | 198 |
| 41 | 1080p Ultra | 166 |
| 29 | 1440p Ultra | 128 |
| 14 | 4K Ultra | 74 |
| Low | Margin of Error | Low |
| 64546 | GB6 Compute Score | 172224 |
| — | Background Blur | 352.4 img/sec |
| — | Face Detection | 229 img/sec |
| — | Horizon Detection | 6.42 Gpixels/sec |
| — | Edge Detection | 8.86 Gpixels/sec |
| — | Gaussian Blur | 7.89 Gpixels/sec |
| — | Feature Matching | 1.5 Gpixels/sec |
| — | Stereo Matching | 662.8 Gpixels/sec |
| — | Particle Physics | 24012 FPS |
| — | API | OpenCL |
| 9029 | G3D Mark Score | 27367 |
| 786 | G2D Mark | 1207 |
| 70 FPS | DirectX 11 | 300 FPS |
| 50 FPS | DirectX 12 | 110 FPS |
| 3702 Ops/s | GPU Compute | 15171 Ops/s |
| 11871 | GB6 ML Single Precision | 34533 |
| 20120 | GB6 ML Half Precision | 42224 |
| 7879 | GB6 ML Quantized | 26568 |
| 5487 | Image Classification (SP) | 15095 |
| 16864 | Image Segmentation (HP) | 21206 |
| 8788 | Image Super Resolution (Q) | 33962 |
| 25029 | Face Detection (HP) | 57614 |
| 18852 | Pose Estimation (Q) | 214748 |
| 2115 | Text Classification (SP) | 4325 |
| 4266 | Machine Translation (HP) | 6598 |
| 7449 | Object Detection (SP) | 16608 |
| 22207 | Depth Estimation (Q) | 57731 |
| 95039 | Style Transfer (SP) | 394987 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 60 GPixel/s | Pixel Fill Rate | 359 GPixel/s |
| 120 GTexel/s | Texture Fill Rate | 718 GTexel/s |
| 7.7 TFLOPS | FLOPS (FP32) | 46 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 16 GB |
| — | Memory Clock | 2250 MHz |
| — | Effective Memory Speed | 18000 Mbps |
| — | Bus | 256-bit |
| No | ECC | No |
| — | Memory Bandwidth | 576 GB/s |
| PCIe 5.0 | Interface | PCIe 4.0 x16 |
| — | TGP | 260 W |
| TSMC | Manufacturing | TSMC |
| 3 nm | Fabrication Process | 5 nm |
| — | Die Size | 529 mm² |
| — | Transistor Count | 57 billion |
| — | Transistor Density | 107.75 MTr/mm² |
| 12.1 | DirectX | 12 |
| 1.4 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.2 |
| — | CUDA | — |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| 2.1 | DisplayPort | 2.1 |
| Intel | Vendor | Amd |
| Integrated | Build | Discrete |
| January 5, 2026 | Released | — |
| Laptop | Case | Desktop |
| Gaming | Purpose | Gaming |
| Mid-range | Segment | High-end |
| Celestial | Architecture | RDNA 3.0 |
| Panther Lake | GPU Codename | Navi 31 |
| -Intel Core Ultra X9 388Hor above | Recommended CPU | — |
| 4242 | Steel Nomad Lite Score | 21359 |
| 6595 | Time Spy | 22537 |
| 26399 | Solar Bay | 90757 |
| 3886 | Port Royal | 12461 |
| 16770 | Fire Strike | 56212 |
| 11707 | Wild Life Extreme | 41740 |
| 68498 | Night Raid | 169038 |
| 300 MHz | Base Clock | 1287 MHz |
| 2500 MHz | Boost Clock | 2245 MHz |
| 1536 | Shading Units | 5120 |
| 48 | Texture Mapping Units (TMUs) | 320 |
| 24 | Render Output Units (ROPs) | 160 |
| 12 | Compute Units (Pipelines) | — |
| — | Tensor Cores | — |
| — | Ray-tracing Cores | 80 |
| 64KB per cluster | L1 Cache | 256KB per cluster |
| 16MB shared | L2 Cache | 6MB shared |
| 2 IPC | Instructions Per Cycle | 4 IPC |