AMD Radeon RX 9070 XT vs 7900 XT
AMD Radeon RX 9070 XT
Navi 48
AMD Radeon RX 7900 XT
Navi 31
We compared two discrete desktop gaming GPUs: the Radeon RX 9070 XT 16 GB with 64 pipelines and 4096 shaders against the 1 year and 1 month older 7900 XT 20 GB that utilizes 5376 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 9070 XT
- Manufactured using a more efficient 4 nm process technology
- Shows 7% higher average frame rate in modern games at QHD resolution – 152 vs 142 FPS
Reasons to consider the Radeon RX 7900 XT
- Includes 4 GB more video memory
- Has 24% higher memory bandwidth: 800 vs 644.6 GB/s
- Has 31% more shading units (5376 vs 4096)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 242 169 149 109 |
235 160 141 107 |
| The Witcher 3 | 267 237 167 89 |
249 225 160 87 |
| Counter-Strike 2 | 325 224 163 82 |
311 222 157 81 |
| Far Cry 6 | 198 176 163 104 |
196 168 151 100 |
| Hogwarts Legacy | 162 133 107 58 |
153 124 98 56 |
| CoD: Modern Warfare III | 240 232 174 118 |
228 214 163 108 |
| Ghost of Tsushima | 158 137 116 73 |
150 126 109 69 |
| Cyberpunk 2077 | 190 171 119 53 |
181 156 108 49 |
| Shadow of the Tomb Raider | 280 265 207 107 |
271 258 189 101 |
| 1080p High | 229 | 219 |
| 1080p Ultra | 194 | 184 |
| 1440p Ultra | 152 | 142 |
| 4K Ultra | 88 | 84 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 29556 | 27106 |
| Solar Bay | 122220 | 105357 |
| Port Royal | 18363 | 14360 |
| Fire Strike | 66319 | 67227 |
| Wild Life Extreme | 54672 | 48410 |
| Night Raid | 194947 | 176232 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 427.4 img/sec | 419.8 img/sec |
| Face Detection | 251 img/sec | 240.5 img/sec |
| Horizon Detection | 6.77 Gpixels/sec | 8.72 Gpixels/sec |
| Edge Detection | 9.42 Gpixels/sec | 12 Gpixels/sec |
| Gaussian Blur | 9.35 Gpixels/sec | 9.88 Gpixels/sec |
| Feature Matching | 1.42 Gpixels/sec | 1.71 Gpixels/sec |
| Stereo Matching | 651.4 Gpixels/sec | 701.7 Gpixels/sec |
| Particle Physics | 23630 FPS | 26631.4 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 1310 | 1247 |
| DirectX 11 | 295 FPS | 341 FPS |
| DirectX 12 | 77 FPS | 112 FPS |
| GPU Compute | 16100 Ops/s | 16878 Ops/s |
Blender
Blender GPU
Recent User Tests
Radeon RX 9070 XT
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-07-12 (luizmdd) | Cinebench 2024 | 50113 |
| 📘 2026-07-04 -> StevenS | Geekbench 6 OpenCL | 179283 |
| 📘 2026-07-04 -> StevenS | Steel Nomad Light | 27505 |
| 📘 2025-10-15 (adv) | Geekbench 6 OpenCL | 175418 |
Radeon RX 7900 XT
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-01-01 (Mr Scare) | Cinebench 2024 | 11648 |
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) | 18001 | 16951 |
| Image Segmentation (HP) | 25174 | 23234 |
| Image Super Resolution (Q) | 45714 | 41128 |
| Face Detection (HP) | 74776 | 67615 |
| Pose Estimation (Q) | 196137 | 237026 |
| Text Classification (SP) | 5163 | 4961 |
| Machine Translation (HP) | 8677 | 7043 |
| Object Detection (SP) | 19602 | 18737 |
| Depth Estimation (Q) | 74879 | 67746 |
| Style Transfer (SP) | 411302 | 457919 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of Radeon RX 9070 XT and 7900 XTGeneral
| Vendor | Amd | Amd |
| Build | Discrete | Discrete |
| Released | January 7, 2025 | December 13, 2023 |
| Launch price (MSRP) | $599 | $899 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | High-end | High-end |
| Architecture | RDNA 4.0 | RDNA 3.0 |
| GPU Codename | Navi 48 | Navi 31 |
| Rival Equivalent | - GeForce RTX 5070 Ti | - GeForce RTX 4080 |
| Recommended CPU | - Intel Core Ultra 5 245K or above | - Intel Core i7 13700K or above |
Desktop GPU rating (12th and 11th place)
Graphics Processing Unit
| Base Clock | 1660 MHz | 1387 MHz |
| Boost Clock | 2970 MHz | 2394 MHz |
| Shading Units | 4096 | 5376 |
| Texture Mapping Units (TMUs) | 256 | 336 |
| Render Output Units (ROPs) | 128 | 192 |
| Compute Units (Pipelines) | 64 | - |
| Tensor Cores | 128 | - |
| Ray-tracing Cores | 64 | 84 |
| L1 Cache | 128KB per cluster | 256KB per cluster |
| L2 Cache | 8MB shared | 6MB shared |
| Instructions Per Cycle | 4 IPC | 4 IPC |
Raw Performance
| Pixel Fill Rate | 380 GPixel/s | 460 GPixel/s |
| Texture Fill Rate | 760 GTexel/s | 804 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 5.0 x16 | PCIe 4.0 x16 |
| TGP | 304 W | 300 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 4 nm | 5 nm |
| Die Size | 357 mm² | 529 mm² |
| Transistor Count | 53.9 billion | 57 billion |
| Transistor Density | 150.98 MTr/mm² | 107.75 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR6 |
| Memory Size | 16 GB | 20 GB |
| Memory Clock | 2518 MHz | 2500 MHz |
| Effective Memory Speed | 20100 Mbps | 20000 Mbps |
| Bus | 256-bit | 320-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12.2 | 12 |
| Vulkan | 1.4 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.2 | 2.2 |
| CUDA | No | - |
| Ray Tracing | Yes | Yes |
| DLSS | No | No |
| DisplayPort | 2.1a | 2.1 |
Cast your vote
Total votes: 119