Quick/Comparisons
12 | Gaming | 33 |
17 | Workstation | 35 |
18 | AI/ML |
Compare with something else?
Compare Radeon 890M with another →35 |
85 | Energy Efficiency | 46 |
26 | Quick Comparison Final Score | 34 |
| Strix Point | Graphics Processor | Navi 33 |
| 1024 | Cores | 2048 |
| 64 / 32 | TMUs / ROPs | 128 / 64 |
| 311.81 | Blender GPU | 1271.01 |
| 28 | Forza Horizon 5 | 80 |
| 28 | The Witcher 3 | 108 |
| 32 | Counter-Strike 2 | 138 |
| 38 | Far Cry 6 | 96 |
| 19 | Hogwarts Legacy | 64 |
| 32 | Call of Duty | 96 |
| 16 | Ghost of Tsushima | 65 |
| 22 | Cyberpunk 2077 | 68 |
| 35 | Tomb Raider | 120 |
| 28 | Average FPS | 93 |
| 38 | 1080p High | 119 |
| 28 | 1080p Ultra | 93 |
| 19 | 1440p Ultra | 66 |
| 10 | 4K Ultra | 37 |
| Low | Margin of Error | Low |
| 42932 | GB6 Compute Score | 82731 |
| 98.6 img/sec | Background Blur | 201.7 img/sec |
| 42 img/sec | Face Detection | 110.3 img/sec |
| 1.25 Gpixels/sec | Horizon Detection | 3.05 Gpixels/sec |
| 1.6 Gpixels/sec | Edge Detection | 4.12 Gpixels/sec |
| 1.69 Gpixels/sec | Gaussian Blur | 3.72 Gpixels/sec |
| 0.55 Gpixels/sec | Feature Matching | 0.91 Gpixels/sec |
| 214.8 Gpixels/sec | Stereo Matching | 266.1 Gpixels/sec |
| 7757.7 FPS | Particle Physics | 9727.4 FPS |
| OpenCL | API | OpenCL |
| 8122 | G3D Mark Score | 16519 |
| 976 | G2D Mark | 986 |
| 73 FPS | DirectX 11 | 172 FPS |
| 37 FPS | DirectX 12 | 57 FPS |
| 4164 Ops/s | GPU Compute | 8763 Ops/s |
| 9613 | GB6 ML Single Precision | 20579 |
| 15157 | GB6 ML Half Precision | 26805 |
| 7082 | GB6 ML Quantized | 16792 |
| 3563 | Image Classification (SP) | 10305 |
| 6170 | Image Segmentation (HP) | 11405 |
| 10762 | Image Super Resolution (Q) | 25104 |
| 13773 | Face Detection (HP) | 34286 |
| 37861 | Pose Estimation (Q) | 91413 |
| 2572 | Text Classification (SP) | 3906 |
| 4699 | Machine Translation (HP) | 5084 |
| 2845 | Object Detection (SP) | 7217 |
| 17260 | Depth Estimation (Q) | 42955 |
| 86751 | Style Transfer (SP) | 178703 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 93 GPixel/s | Pixel Fill Rate | 170 GPixel/s |
| 186 GTexel/s | Texture Fill Rate | 340 GTexel/s |
| 5.9 TFLOPS | FLOPS (FP32) | 21.7 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 8 GB |
| — | Memory Clock | 2250 MHz |
| — | Effective Memory Speed | 18000 Mbps |
| — | Bus | 128-bit |
| — | ECC | No |
| — | Memory Bandwidth | 288 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x8 |
| 15-54 W (configurable) | TGP | 165 W |
| TSMC | Manufacturing | TSMC |
| 4 nm | Fabrication Process | 6 nm |
| 233 mm² | Die Size | 204 mm² |
| 34 billion | Transistor Count | 13 billion |
| 145.92 MTr/mm² | Transistor Density | 63.73 MTr/mm² |
| None | CUDA | — |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| 2.1 | DisplayPort | 2.1 |
| 12 | DirectX | 12 |
| 1.4 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 2.1 | OpenCL | 2.2 |
| Amd | Vendor | Amd |
| Integrated | Build | Discrete |
| June 3, 2024 | Released | May 24, 2023 |
| Laptop | Case | Desktop |
| Generic | Purpose | Gaming |
| Mid-range | Segment | Mid-range |
| RDNA 3.5 | Architecture | RDNA 3.0 |
| Strix Point | GPU Codename | Navi 33 |
| -AMD Ryzen AI 9 HX 370or above | Recommended CPU | -Intel Core i5 13500or above |
| 3190 | Steel Nomad Lite Score | 10061 |
| 3307 | Time Spy | 10930 |
| 15184 | Solar Bay | 44092 |
| 1790 | Port Royal | 5669 |
| 8885 | Fire Strike | 31171 |
| 6775 | Wild Life Extreme | 19843 |
| 37532 | Night Raid | 119706 |
| 400 MHz | Base Clock | 1720 MHz |
| 2900 MHz | Boost Clock | 2655 MHz |
| 1024 | Shading Units | 2048 |
| 64 | Texture Mapping Units (TMUs) | 128 |
| 32 | Render Output Units (ROPs) | 64 |
| 16 | Compute Units (Pipelines) | — |
| No | Tensor Cores | No |
| 16 | Ray-tracing Cores | 32 |
| 512KB per cluster | L1 Cache | 128KB per cluster |
| 2MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 4 IPC |