Nvidia RTX Pro 6000 Blackwell
- Graphics Processor: GB202-300-A1
- Cores: 24064
- TMUs / ROPs: 752 / 190
Review
Compare Nvidia RTX Pro 6000 Blackwell with other GPUs
Games
| Forza Horizon 5 | 309 235 215 175 |
| The Witcher 3 | 343 311 216 116 |
| Counter-Strike 2 | 362 263 203 93 |
| Far Cry 6 | 221 198 185 112 |
| Hogwarts Legacy | 235 189 150 89 |
| CoD: Modern Warfare III | 305 296 252 176 |
| Ghost of Tsushima | 206 170 158 107 |
| Cyberpunk 2077 | 253 221 160 71 |
| Shadow of the Tomb Raider | 319 298 224 121 |
| 1080p High | 284 |
| 1080p Ultra | 242 |
| 1440p Ultra | 196 |
| 4K Ultra | 118 |
| Margin of Error | High |
Test in Benchmarks
Performance tests in graphics benchmarks and applications3D Mark
| Time Spy | 42614 |
| Solar Bay | 255911 |
| Port Royal | 39888 |
| Fire Strike | 75325 |
| Wild Life Extreme | 110070 |
| Night Raid | 214655 |
GeekBench 6 OpenCL
| Background Blur | 366.1 img/sec |
| Face Detection | 248 img/sec |
| Horizon Detection | 23.3 Gpixels/sec |
| Edge Detection | 35.2 Gpixels/sec |
| Gaussian Blur | 45 Gpixels/sec |
| Feature Matching | 2.47 Gpixels/sec |
| Stereo Matching | 3040 Gpixels/sec |
| Particle Physics | 42574.6 FPS |
| API | OpenCL |
Passmark Graphics
| G2D Mark | 1391 |
| DirectX 11 | 339 FPS |
| DirectX 12 | 154 FPS |
| GPU Compute | 26607 Ops/s |
Artificial Intelligence Tests
Performance in machine learning and artificial intelligence tasksGeekBench 6 ML
| Image Classification (SP) | 16903 |
| Image Segmentation (HP) | 48518 |
| Image Super Resolution (Q) | 54618 |
| Face Detection (HP) | 103224 |
| Pose Estimation (Q) | 338587 |
| Text Classification (SP) | 3894 |
| Machine Translation (HP) | 7291 |
| Object Detection (SP) | 26498 |
| Depth Estimation (Q) | 90853 |
| Style Transfer (SP) | 635289 |
| Framework | ONNX |
| Backend | DirectML |
Specifications
Detailed technical specifications of the Nvidia RTX Pro 6000 BlackwellGeneral
| Vendor | Nvidia |
| Build | Discrete |
| Released | March 18, 2026 |
| Launch price (MSRP) | $8559 |
| Case | Desktop |
| Purpose | Professional |
| Segment | High-end |
| Architecture | Blackwell 2.0 |
| GPU Codename | GB202-300-A1 |
| Recommended CPU | - AMD Ryzen 9 9955HX3D or above |
Desktop GPU rating - 1st place
Graphics Processing Unit
| Base Clock | 1590 MHz |
| Boost Clock | 2617 MHz |
| Shading Units | 24064 |
| Texture Mapping Units (TMUs) | 752 |
| Render Output Units (ROPs) | 190 |
| Compute Units (Pipelines) | 188 |
| Tensor Cores | 752 |
| Ray-tracing Cores | 188 |
| L1 Cache | 128KB per cluster |
| L2 Cache | 128MB shared |
| Instructions Per Cycle | 2 IPC |
Raw Performance
| Pixel Fill Rate | 497 GPixel/s |
| Texture Fill Rate | 1968 GTexel/s |
Physical
| Interface | PCIe 5.0 x16 |
| TGP | 600 W |
| Manufacturing | TSMC |
| Fabrication Process | 5 nm |
| Die Size | 750 mm² |
| Transistor Count | 92.2 billion |
| Transistor Density | 122.93 MTr/mm² |
Memory
| Memory Type | GDDR7 |
| Memory Size | 96 GB |
| Memory Clock | 1750 MHz |
| Effective Memory Speed | 28000 Mbps |
| Bus | 512-bit |
| ECC | Yes |
API
| DirectX | 12.2 |
| Vulkan | 1.4 |
| OpenGL | 4.6 |
| OpenCL | 3.0 |
| CUDA | 12 |
| Ray Tracing | Yes |
| DLSS | DLSS 4 |
| DisplayPort | 2.1b |