AMD Radeon RX 6900 XT vs GeForce RTX 3090
VS
AMD Radeon RX 6900 XT
Navi 21
Nvidia GeForce RTX 3090
GA102
We compared two discrete desktop gaming GPUs: the Radeon RX 6900 XT 16 GB with 5120 shaders against the 3 months older GeForce RTX 3090 24 GB that utilizes 82 pipelines and 10496 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.
Review
Gaming
Performance in DirectX, OpenCL, and Vulkan games
Workstation
Perf. in 3D modeling, video editing and rendering apps
AI/ML
Capabilities for machine learning and AI-related tasks
Energy Efficiency
Power consumption efficiency in different scenarios
NanoReview Final Score
Overall video card score
Value for money (Beta)
Key differences
Reasons to consider the Radeon RX 6900 XT
- Manufactured using a more efficient 7 nm process technology
Reasons to consider the GeForce RTX 3090
- 55% higher maximum theoretical performance (35.6 vs 23 TFLOPS)
- Includes 8 GB more video memory
- Supports Nvidia DLSS 2 technology
- Has 83% higher memory bandwidth: 936.2 vs 512 GB/s
- Achieves 71% more points in the GeekBench 6 Compute test (211K vs 124K)
- Has 2.1x more shading units (10496 vs 5120)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 212 139 117 90 |
186 128 117 91 |
| The Witcher 3 | 209 186 138 71 |
205 170 128 66 |
| Counter-Strike 2 | 296 213 153 81 |
275 207 155 83 |
| Far Cry 6 | 173 147 131 83 |
156 145 124 77 |
| Hogwarts Legacy | 129 107 80 46 |
128 108 86 47 |
| CoD: Modern Warfare III | 186 178 128 85 |
171 159 123 80 |
| Ghost of Tsushima | 129 112 92 55 |
120 97 85 48 |
| Cyberpunk 2077 | 142 127 86 42 |
148 132 90 43 |
| Shadow of the Tomb Raider | 228 213 161 80 |
237 226 168 91 |
| 1080p High | 189 | 181 |
| 1080p Ultra | 158 | 152 |
| 1440p Ultra | 121 | 120 |
| 4K Ultra | 70 | 70 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 20817 | 19896 |
| Solar Bay | 86965 | 97395 |
| Port Royal | 10543 | 13633 |
| Fire Strike | 57312 | 47512 |
| Wild Life Extreme | 39345 | 43669 |
| Night Raid | 159536 | 139766 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 231.6 img/sec | 320.8 img/sec |
| Face Detection | 152.5 img/sec | 207.2 img/sec |
| Horizon Detection | 4.26 Gpixels/sec | 10.1 Gpixels/sec |
| Edge Detection | 5.75 Gpixels/sec | 14.4 Gpixels/sec |
| Gaussian Blur | 5.87 Gpixels/sec | 11.5 Gpixels/sec |
| Feature Matching | 1.12 Gpixels/sec | 1.48 Gpixels/sec |
| Stereo Matching | 618.7 Gpixels/sec | 984.2 Gpixels/sec |
| Particle Physics | 17973.9 FPS | 27764.9 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 1063 | 1069 |
| DirectX 11 | 279 FPS | 218 FPS |
| DirectX 12 | 111 FPS | 109 FPS |
| GPU Compute | 14302 Ops/s | 15028 Ops/s |
Blender
Blender GPU
Recent User Tests
Radeon RX 6900 XT
| Date | Benchmark | Result |
|---|---|---|
| 📘 2025-12-04 -> phillybass | Cinebench 2024 | 8430 |
GeForce RTX 3090
No benchmark results yet
Artificial Intelligence Tests
Performance in machine learning and artificial intelligence tasksGeekBench 6 ML
GB6 ML Single Precision
GB6 ML Half Precision
GB6 ML Quantized
| Image Classification (SP) | 13868 | 10665 |
| Image Segmentation (HP) | 17467 | 28963 |
| Image Super Resolution (Q) | 32396 | 22697 |
| Face Detection (HP) | 47808 | 55232 |
| Pose Estimation (Q) | 178873 | 128155 |
| Text Classification (SP) | 4358 | 3152 |
| Machine Translation (HP) | 7910 | 5088 |
| Object Detection (SP) | 15394 | 13891 |
| Depth Estimation (Q) | 57351 | 37984 |
| Style Transfer (SP) | 372610 | 272000 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of Radeon RX 6900 XT and GeForce RTX 3090General
| Vendor | Amd | Nvidia |
| Build | Discrete | Discrete |
| Released | December 8, 2020 | September 24, 2020 |
| Launch price (MSRP) | $999 | $1499 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | High-end | High-end |
| Architecture | RDNA 2.0 | Ampere |
| GPU Codename | Navi 21 | GA102 |
| Rival Equivalent | - GeForce RTX 4070 | - Radeon RX 6900 XT |
| Successor | - Radeon RX 7900 XT | - GeForce RTX 5090 |
| Recommended CPU | - Intel Core i7 12700K or above | - Intel Core i9 12900K or above |
Desktop GPU rating (26th and 20th place)
Graphics Processing Unit
| Base Clock | 1825 MHz | 1395 MHz |
| Boost Clock | 2250 MHz | 1695 MHz |
| Shading Units | 5120 | 10496 |
| Texture Mapping Units (TMUs) | 320 | 328 |
| Render Output Units (ROPs) | 128 | 112 |
| Compute Units (Pipelines) | - | 82 |
| Tensor Cores | - | 328 |
| Ray-tracing Cores | 80 | 82 |
| L1 Cache | 128KB per cluster | 128KB per cluster |
| L2 Cache | 4MB shared | 6MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 288 GPixel/s | 190 GPixel/s |
| Texture Fill Rate | 720 GTexel/s | 556 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| TGP | 300 W | 350 W |
| Manufacturing | TSMC | Samsung |
| Fabrication Process | 7 nm | 8 nm |
| Die Size | 520 mm² | 628 mm² |
| Transistor Count | 26 billion | 28 billion |
| Transistor Density | 50 MTr/mm² | 44.59 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR6X |
| Memory Size | 16 GB | 24 GB |
| Memory Clock | 2000 MHz | 1219 MHz |
| Effective Memory Speed | 16000 Mbps | 19500 Mbps |
| Bus | 256-bit | 384-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12 | 12 |
| Vulkan | 1.3 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| CUDA | - | 8.6 |
| Ray Tracing | Yes | Yes |
| DLSS | No | DLSS 2 |
| DisplayPort | 1.4a | 1.4a |
Cast your vote
Total votes: 43