AMD Radeon RX 9070 vs GeForce RTX 4060 Ti 16GB
VS
AMD Radeon RX 9070
Navi 48
We compared two discrete desktop gaming GPUs: the Radeon RX 9070 with 56 pipelines and 3584 shaders against the 1 year and 6 months older GeForce RTX 4060 Ti 16GB that utilizes 34 pipelines and 4352 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
Scores marked with a red asterisk (**) represent initial estimates from early testing.
Value for money (Beta)
Key differences
Reasons to consider the Radeon RX 9070
- Performs significantly better (up to 68%) in 3DMark Steel Nomad Lite
- Shows 62% higher average frame rate in modern games at QHD resolution – 139 vs 86 FPS
- 63% higher maximum theoretical performance (36.1 vs 22.1 TFLOPS)
- Manufactured using a more efficient 4 nm process technology
- Has 2.2x higher memory bandwidth: 644.6 vs 288 GB/s
Reasons to consider the GeForce RTX 4060 Ti 16GB
- Supports Nvidia DLSS 3 technology
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 229 156 137 102 |
144 94 83 62 |
| The Witcher 3 | 240 216 159 84 |
172 141 99 53 |
| Counter-Strike 2 | 307 215 158 84 |
245 190 132 76 |
| Far Cry 6 | 192 163 148 95 |
129 117 92 56 |
| Hogwarts Legacy | 146 119 97 52 |
95 81 62 32 |
| CoD: Modern Warfare III | 219 212 157 107 |
118 112 81 52 |
| Ghost of Tsushima | 146 122 105 65 |
88 75 57 31 |
| Cyberpunk 2077 | 174 149 102 47 |
105 92 56 26 |
| Shadow of the Tomb Raider | 262 248 188 99 |
161 147 111 59 |
| 1080p High | 213 | 140 |
| 1080p Ultra | 178 | 117 |
| 1440p Ultra | 139 | 86 |
| 4K Ultra | 82 | 50 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 26693 | 13456 |
| Solar Bay | 106118 | 62446 |
| Port Royal | 15939 | 8119 |
| Fire Strike | 60053 | 34258 |
| Wild Life Extreme | 48323 | 25587 |
| Night Raid | 177554 | 135657 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 377.5 img/sec | 232.6 img/sec |
| Face Detection | 221.3 img/sec | 138.4 img/sec |
| Horizon Detection | 6.4 Gpixels/sec | 4.68 Gpixels/sec |
| Edge Detection | 8.99 Gpixels/sec | 6.06 Gpixels/sec |
| Gaussian Blur | 8.52 Gpixels/sec | 6.99 Gpixels/sec |
| Feature Matching | 1.36 Gpixels/sec | 1.6 Gpixels/sec |
| Stereo Matching | 606 Gpixels/sec | 652.6 Gpixels/sec |
| Particle Physics | 8521.2 FPS | 19534.7 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 1262 | 1078 |
| DirectX 11 | 280 FPS | 199 FPS |
| DirectX 12 | 73 FPS | 89 FPS |
| GPU Compute | 14799 Ops/s | 11953 Ops/s |
Blender
Blender GPU
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) | 15375 | - |
| Image Segmentation (HP) | 37834 | - |
| Image Super Resolution (Q) | 43910 | - |
| Face Detection (HP) | 67858 | - |
| Pose Estimation (Q) | 172939 | - |
| Text Classification (SP) | 4469 | - |
| Machine Translation (HP) | 8499 | - |
| Object Detection (SP) | 15393 | - |
| Depth Estimation (Q) | 66890 | - |
| Style Transfer (SP) | 365633 | - |
| Framework | ONNX | - |
| Backend | DirectML | - |
Specifications
Technical specifications of Radeon RX 9070 and GeForce RTX 4060 Ti 16GBGeneral
| Vendor | Amd | Nvidia |
| Build | Discrete | Discrete |
| Released | January 7, 2025 | July 18, 2023 |
| Launch price (MSRP) | $549 | $499 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | High-end | Mid-range |
| Architecture | RDNA 4.0 | Ada Lovelace |
| GPU Codename | Navi 48 | AD106 |
| Rival Equivalent | - GeForce RTX 5070 | - |
| Successor | - | - GeForce RTX 5060 Ti (16GB) |
| Recommended CPU | - Intel Core Ultra 5 245K or above | - Intel Core i5 14600K or above |
Desktop GPU rating (16th and 40th place)
Graphics Processing Unit
| Base Clock | 1330 MHz | 2310 MHz |
| Boost Clock | 2520 MHz | 2535 MHz |
| Shading Units | 3584 | 4352 |
| Texture Mapping Units (TMUs) | 224 | 136 |
| Render Output Units (ROPs) | 128 | 48 |
| Compute Units (Pipelines) | 56 | 34 |
| Tensor Cores | 112 | 136 |
| Ray-tracing Cores | 56 | 34 |
| L1 Cache | 128KB per cluster | 128KB per cluster |
| L2 Cache | 8MB shared | 32MB shared |
| Instructions Per Cycle | 4 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 323 GPixel/s | 122 GPixel/s |
| Texture Fill Rate | 564 GTexel/s | 345 GTexel/s |
FLOPS (FP32)
Differences in GPUs' instructions per clock make TFLOPS values not directly comparable.
Physical
| Interface | PCIe 5.0 x16 | PCIe 4.0 x8 |
| TGP | 220 W | 165 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 4 nm | 5 nm |
| Die Size | 357 mm² | 188 mm² |
| Transistor Count | 53.9 billion | 22 billion |
| Transistor Density | 150.98 MTr/mm² | 117.02 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR6 |
| Memory Size | 16 GB | 16 GB |
| Memory Clock | 2518 MHz | 2250 MHz |
| Effective Memory Speed | 20100 Mbps | 18000 Mbps |
| Bus | 256-bit | 128-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12.2 | 12 |
| Vulkan | 1.4 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.2 | 3.0 |
| CUDA | No | 8.9 |
| Ray Tracing | Yes | Yes |
| DLSS | No | DLSS 3 |
| DisplayPort | 2.1a | 1.4a |
Cast your vote
Total votes: 14