Quick/Comparisons
30 | Gaming | 56 |
34 | Workstation | 55 |
31 | AI/ML |
Compare with something else?
Compare Radeon RX 6650 with another →54 |
39 | Energy Efficiency | 45 |
31 | Quick Comparison Final Score | 55 |
| Navi 23 | Graphics Processor | Navi 32 |
| 2048 | Cores | 3840 |
| 128 / 64 | TMUs / ROPs | 240 / 96 |
| 1138.24 | Blender GPU | 2417.04 |
| 76 | Forza Horizon 5 | 136 |
| 101 | The Witcher 3 | 177 |
| 130 | Counter-Strike 2 | 205 |
| 93 | Far Cry 6 | 146 |
| 59 | Hogwarts Legacy | 102 |
| 87 | Call of Duty | 164 |
| 63 | Ghost of Tsushima | 102 |
| 65 | Cyberpunk 2077 | 122 |
| 111 | Tomb Raider | 193 |
| 87 | Average FPS | 150 |
| 112 | 1080p High | 181 |
| 87 | 1080p Ultra | 150 |
| 61 | 1440p Ultra | 114 |
| 32 | 4K Ultra | 67 |
| Low | Margin of Error | Low |
| 90831 | GB6 Compute Score | 148335 |
| 220.1 img/sec | Background Blur | 300.7 img/sec |
| 128.3 img/sec | Face Detection | 200.5 img/sec |
| 2.94 Gpixels/sec | Horizon Detection | 5.77 Gpixels/sec |
| 4.13 Gpixels/sec | Edge Detection | 8.05 Gpixels/sec |
| 3.68 Gpixels/sec | Gaussian Blur | 6.44 Gpixels/sec |
| 0.94 Gpixels/sec | Feature Matching | 1.25 Gpixels/sec |
| 408.2 Gpixels/sec | Stereo Matching | 566.4 Gpixels/sec |
| 10694.7 FPS | Particle Physics | 20533.6 FPS |
| OpenCL | API | OpenCL |
| 17117 | G3D Mark Score | 24337 |
| 924 | G2D Mark | 1191 |
| 168 FPS | DirectX 11 | 249 FPS |
| 62 FPS | DirectX 12 | 95 FPS |
| 7461 Ops/s | GPU Compute | 13568 Ops/s |
| 17945 | GB6 ML Single Precision | 31216 |
| 21242 | GB6 ML Half Precision | 37266 |
| 13940 | GB6 ML Quantized | 24564 |
| 8220 | Image Classification (SP) | 13913 |
| 9263 | Image Segmentation (HP) | 18416 |
| 20723 | Image Super Resolution (Q) | 31387 |
| 27074 | Face Detection (HP) | 51780 |
| 76541 | Pose Estimation (Q) | 177217 |
| 2796 | Text Classification (SP) | 3655 |
| 4281 | Machine Translation (HP) | 6216 |
| 6880 | Object Detection (SP) | 15073 |
| 33354 | Depth Estimation (Q) | 57318 |
| 185358 | Style Transfer (SP) | 347420 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 169 GPixel/s | Pixel Fill Rate | 233 GPixel/s |
| 337 GTexel/s | Texture Fill Rate | 583 GTexel/s |
| 10.8 TFLOPS | FLOPS (FP32) | 37.3 TFLOPS |
| GDDR6 | Memory Type | GDDR6 |
| 8 GB | Memory Size | 16 GB |
| 2190 MHz | Memory Clock | 2438 MHz |
| 17500 Mbps | Effective Memory Speed | 19500 Mbps |
| 128-bit | Bus | 256-bit |
| No | ECC | No |
| 280.3 GB/s | Memory Bandwidth | 624.1 GB/s |
| PCIe 4.0 x8 | Interface | PCIe 4.0 x16 |
| 176 W | TGP | 263 W |
| TSMC | Manufacturing | TSMC |
| 7 nm | Fabrication Process | 5 nm |
| 237 mm² | Die Size | 346 mm² |
| 11 billion | Transistor Count | 28 billion |
| 46.41 MTr/mm² | Transistor Density | 80.92 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 2.1 | OpenCL | 2.2 |
| — | CUDA | — |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| 1.4a | DisplayPort | 2.1 |
| Amd | Vendor | Amd |
| Discrete | Build | Discrete |
| May 10, 2022 | Released | September 6, 2023 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| High-end | Segment | High-end |
| RDNA 2.0 | Architecture | RDNA 3.0 |
| Navi 23 | GPU Codename | Navi 32 |
| -Intel Core i5 12600Kor above | Recommended CPU | -Intel Core i5 13600Kor above |
| 9265 | Steel Nomad Lite Score | 18090 |
| 9897 | Time Spy | 20088 |
| 38892 | Solar Bay | 80288 |
| 4897 | Port Royal | 10921 |
| 29357 | Fire Strike | 50041 |
| 18034 | Wild Life Extreme | 37094 |
| 116256 | Night Raid | 160328 |
| 2055 MHz | Base Clock | 1295 MHz |
| 2635 MHz | Boost Clock | 2430 MHz |
| 2048 | Shading Units | 3840 |
| 128 | Texture Mapping Units (TMUs) | 240 |
| 64 | Render Output Units (ROPs) | 96 |
| — | Compute Units (Pipelines) | — |
| No | Tensor Cores | — |
| 32 | Ray-tracing Cores | 60 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 2MB shared | L2 Cache | 4MB shared |
| 2 IPC | Instructions Per Cycle | 4 IPC |