Quick/Comparisons
12 | Gaming | 53 |
17 | Workstation | 50 |
18 | AI/ML |
Compare with something else?
Compare Radeon 890M with another →51 |
85 | Energy Efficiency | 36 |
26 | Quick Comparison Final Score | 51 |
| Strix Point | Graphics Processor | Navi 21 |
| 1024 | Cores | 4608 |
| 64 / 32 | TMUs / ROPs | 288 / 128 |
| 311.81 | Blender GPU | 2413.97 |
| 28 | Forza Horizon 5 | 132 |
| 28 | The Witcher 3 | 175 |
| 32 | Counter-Strike 2 | 201 |
| 38 | Far Cry 6 | 139 |
| 19 | Hogwarts Legacy | 97 |
| 32 | Call of Duty | 161 |
| 16 | Ghost of Tsushima | 103 |
| 22 | Cyberpunk 2077 | 118 |
| 35 | Tomb Raider | 190 |
| 28 | Average FPS | 146 |
| 38 | 1080p High | 178 |
| 28 | 1080p Ultra | 146 |
| 19 | 1440p Ultra | 112 |
| 10 | 4K Ultra | 64 |
| Low | Margin of Error | Low |
| 42932 | GB6 Compute Score | 138858 |
| 98.6 img/sec | Background Blur | 335.7 img/sec |
| 42 img/sec | Face Detection | 221.1 img/sec |
| 1.25 Gpixels/sec | Horizon Detection | 6.16 Gpixels/sec |
| 1.6 Gpixels/sec | Edge Detection | 8.96 Gpixels/sec |
| 1.69 Gpixels/sec | Gaussian Blur | 7.44 Gpixels/sec |
| 0.55 Gpixels/sec | Feature Matching | 1.31 Gpixels/sec |
| 214.8 Gpixels/sec | Stereo Matching | 263 Gpixels/sec |
| 7757.7 FPS | Particle Physics | 14755 FPS |
| OpenCL | API | OpenCL |
| 8122 | G3D Mark Score | 25040 |
| 976 | G2D Mark | 1043 |
| 73 FPS | DirectX 11 | 265 FPS |
| 37 FPS | DirectX 12 | 99 FPS |
| 4164 Ops/s | GPU Compute | 13129 Ops/s |
| 9613 | GB6 ML Single Precision | 30220 |
| 15157 | GB6 ML Half Precision | 30423 |
| 7082 | GB6 ML Quantized | 22583 |
| 3563 | Image Classification (SP) | 11942 |
| 6170 | Image Segmentation (HP) | 7603 |
| 10762 | Image Super Resolution (Q) | 30511 |
| 13773 | Face Detection (HP) | 42862 |
| 37861 | Pose Estimation (Q) | 160019 |
| 2572 | Text Classification (SP) | 4247 |
| 4699 | Machine Translation (HP) | 6279 |
| 2845 | Object Detection (SP) | 13910 |
| 17260 | Depth Estimation (Q) | 51794 |
| 86751 | Style Transfer (SP) | 324124 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 93 GPixel/s | Pixel Fill Rate | 288 GPixel/s |
| 186 GTexel/s | Texture Fill Rate | 648 GTexel/s |
| 5.9 TFLOPS | FLOPS (FP32) | 20.7 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 16 GB |
| — | Memory Clock | 2000 MHz |
| — | Effective Memory Speed | 16000 Mbps |
| — | Bus | 256-bit |
| — | ECC | No |
| — | Memory Bandwidth | 512 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 15-54 W (configurable) | TGP | 300 W |
| TSMC | Manufacturing | TSMC |
| 4 nm | Fabrication Process | 7 nm |
| 233 mm² | Die Size | 520 mm² |
| 34 billion | Transistor Count | 26 billion |
| 145.92 MTr/mm² | Transistor Density | 50 MTr/mm² |
| None | CUDA | — |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| 2.1 | DisplayPort | 1.4a |
| 12 | DirectX | 12 |
| 1.4 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 2.1 | OpenCL | 2.1 |
| Amd | Vendor | Amd |
| Integrated | Build | Discrete |
| June 3, 2024 | Released | November 18, 2020 |
| Laptop | Case | Desktop |
| Generic | Purpose | Gaming |
| Mid-range | Segment | High-end |
| RDNA 3.5 | Architecture | RDNA 2.0 |
| Strix Point | GPU Codename | Navi 21 |
| -AMD Ryzen AI 9 HX 370or above | Recommended CPU | -Intel Core i7 12700Kor above |
| 3190 | Steel Nomad Lite Score | 17589 |
| 3307 | Time Spy | 19370 |
| 15184 | Solar Bay | 78731 |
| 1790 | Port Royal | 9712 |
| 8885 | Fire Strike | 53016 |
| 6775 | Wild Life Extreme | 35632 |
| 37532 | Night Raid | 155398 |
| 400 MHz | Base Clock | 1825 MHz |
| 2900 MHz | Boost Clock | 2250 MHz |
| 1024 | Shading Units | 4608 |
| 64 | Texture Mapping Units (TMUs) | 288 |
| 32 | Render Output Units (ROPs) | 128 |
| 16 | Compute Units (Pipelines) | — |
| No | Tensor Cores | — |
| 16 | Ray-tracing Cores | 72 |
| 512KB per cluster | L1 Cache | 128KB per cluster |
| 2MB shared | L2 Cache | 4MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |