AMD Radeon RX 6800 vs GeForce RTX 4070
VS
AMD Radeon RX 6800
Navi 21
Nvidia GeForce RTX 4070
AD104
We compared two discrete desktop gaming GPUs: the Radeon RX 6800 16 GB with 3840 shaders against the 2 years and 6 months newer GeForce RTX 4070 12 GB that utilizes 46 pipelines and 5888 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 6800
- Includes 4 GB more video memory
Reasons to consider the GeForce RTX 4070
- Performs better (up to 24%) in 3DMark Steel Nomad Lite
- 80% higher maximum theoretical performance (29.1 vs 16.2 TFLOPS)
- Manufactured using a more efficient 5 nm process technology
- Shows 10% higher average frame rate in modern games at QHD resolution – 106 vs 96 FPS
- Supports Nvidia DLSS 3 technology
- Achieves 24% more points in the GeekBench 6 Compute test (167K vs 135K)
- Has 53% more shading units (5888 vs 3840)
- Features 184 tensor cores for effective deep learning and AI workloads
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 175 114 95 66 |
172 115 102 79 |
| The Witcher 3 | 172 148 108 57 |
194 159 114 61 |
| Counter-Strike 2 | 265 193 131 75 |
272 205 149 81 |
| Far Cry 6 | 146 129 106 61 |
149 133 115 68 |
| Hogwarts Legacy | 106 86 68 36 |
117 97 77 39 |
| CoD: Modern Warfare III | 146 135 97 63 |
149 145 107 69 |
| Ghost of Tsushima | 110 89 70 43 |
106 88 72 43 |
| Cyberpunk 2077 | 113 98 65 32 |
129 119 75 37 |
| Shadow of the Tomb Raider | 179 168 122 63 |
211 190 145 80 |
| 1080p High | 157 | 167 |
| 1080p Ultra | 129 | 139 |
| 1440p Ultra | 96 | 106 |
| 4K Ultra | 55 | 62 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 16227 | 17799 |
| Solar Bay | 64715 | 82861 |
| Port Royal | 8145 | 11156 |
| Fire Strike | 44367 | 44067 |
| Wild Life Extreme | 29767 | 35472 |
| Night Raid | 142456 | 153385 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 298.6 img/sec | 233 img/sec |
| Face Detection | 186.2 img/sec | 141.7 img/sec |
| Horizon Detection | 4.75 Gpixels/sec | 6.62 Gpixels/sec |
| Edge Detection | 6.68 Gpixels/sec | 9.19 Gpixels/sec |
| Gaussian Blur | 5.58 Gpixels/sec | 9.2 Gpixels/sec |
| Feature Matching | 1.16 Gpixels/sec | 1.78 Gpixels/sec |
| Stereo Matching | 579 Gpixels/sec | 845.4 Gpixels/sec |
| Particle Physics | 18755.1 FPS | 25043.9 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 1002 | 1165 |
| DirectX 11 | 211 FPS | 243 FPS |
| DirectX 12 | 90 FPS | 103 FPS |
| GPU Compute | 10751 Ops/s | 14570 Ops/s |
Blender
Blender GPU
Recent User Tests
Radeon RX 6800
No benchmark results yet
GeForce RTX 4070
| Date | Benchmark | Result |
|---|---|---|
| 📘 2025-12-14 (kashitsu) | Cinebench 2024 | 18051 |
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) | 11245 | 10246 |
| Image Segmentation (HP) | 13617 | 26153 |
| Image Super Resolution (Q) | 27747 | 32054 |
| Face Detection (HP) | 38124 | 51337 |
| Pose Estimation (Q) | 119493 | 124617 |
| Text Classification (SP) | 2425 | 3703 |
| Machine Translation (HP) | 5228 | 5484 |
| Object Detection (SP) | 11986 | 13134 |
| Depth Estimation (Q) | 46083 | 50548 |
| Style Transfer (SP) | 281860 | 263477 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of Radeon RX 6800 and GeForce RTX 4070General
| Vendor | Amd | Nvidia |
| Build | Discrete | Discrete |
| Released | October 28, 2020 | April 13, 2023 |
| Launch price (MSRP) | $579 | $599 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | High-end | Mid-range |
| Architecture | RDNA 2.0 | Ada Lovelace |
| GPU Codename | Navi 21 | AD104 |
| Rival Equivalent | - GeForce RTX 3060 Ti | - Radeon RX 7900 XT |
| Successor | - | - GeForce RTX 5070 |
| Recommended CPU | - Intel Core i5 12600 or above | - Intel Core i7 14700K or above |
Desktop GPU rating (38th and 28th place)
Graphics Processing Unit
| Base Clock | 1700 MHz | 1920 MHz |
| Boost Clock | 2105 MHz | 2475 MHz |
| Shading Units | 3840 | 5888 |
| Texture Mapping Units (TMUs) | 240 | 184 |
| Render Output Units (ROPs) | 96 | 64 |
| Compute Units (Pipelines) | - | 46 |
| Tensor Cores | No | 184 |
| Ray-tracing Cores | 60 | 46 |
| L1 Cache | 128KB per cluster | 128KB per cluster |
| L2 Cache | 4MB shared | 36MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 202 GPixel/s | 158 GPixel/s |
| Texture Fill Rate | 505 GTexel/s | 455 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| TGP | 250 W | 200 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 7 nm | 5 nm |
| Die Size | 520 mm² | 294 mm² |
| Transistor Count | 26 billion | 35 billion |
| Transistor Density | 50 MTr/mm² | 119.05 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR6X |
| Memory Size | 16 GB | 12 GB |
| Memory Clock | 2000 MHz | 1313 MHz |
| Effective Memory Speed | 16000 Mbps | 21000 Mbps |
| Bus | 256-bit | 192-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 | - | 8.9 |
| Ray Tracing | Yes | Yes |
| DLSS | No | DLSS 3 |
| DisplayPort | 1.4a | 1.4a |
Cast your vote
Total votes: 25