Radeon RX 9070 VS Radeon RX 6800
We are comparing the Radeon RX 9070 (AMD) with the Radeon RX 6800 (AMD). Scroll down to the pros and cons of each graphics card, in-depth specs, and gaming benchmarks.
Last Updated: November 20, 2026
Overall Comparison
KEY DIFFERENCES OF Radeon RX 9070 AND Radeon RX 6800
Here’s how Radeon RX 9070 and Radeon RX 6800 stack up against each other in their most impactful areas.
Why Radeon RX 9070 is the best choice:
-
51% higher 4K Ultra FPS (83 vs 55)
-
46% higher 1440p Ultra FPS (139 vs 95)
-
40% higher 1080p Ultra FPS (180 vs 129)
-
20% higher Boost Clock (2520 MHz vs 2105 MHz)
-
66% higher 3DMark Time Spy score (26923 vs 16214)
SPECIFICATION TABLE COMPARISON OF Radeon RX 9070 AND Radeon RX 6800
Below is the detailed specification table comparing Radeon RX 9070 and Radeon RX 6800.
Note: Highlighted specs mean that GPU wins that spec row.
If neither side is highlighted, it is a tie or there is not enough data for both specs.
| Specification | Radeon RX 9070 | Radeon RX 6800 |
|---|---|---|
|
General Info
|
||
| GPU Name: | Radeon RX 9070 | Radeon RX 6800 |
| GPU Type: | Discrete | Discrete |
| Codename: | Navi 48 | Navi 21 |
| Vendor: | AMD | AMD |
| Foundry: | TSMC | TSMC |
| Architecture: | RDNA 4.0 | RDNA 2.0 |
| Generation: | Navi IV (RX 9000) | Navi II |
| Release Date: | March 6, 2025 | October 28, 2020 |
|
Board Design
|
||
| Bus Interface: | PCIe 5.0 x16 | PCIe 4.0 x16 |
| PCIe Version: | 5.0 | 4.0 |
| PCIe Lanes: | x16 | x16 |
| Process Size: | 4 nm | 7 nm |
| Transistors: | 53.9 billion | 26.8 billion |
| Density: | 151.19 MTr/mm² | 51.5 MTr/mm² |
| Die Size: | 356.5 | 520 mm² |
| Board Length: | — | 267 mm |
| Board Width: | — | 40 mm |
| Board Height: | — | 120 mm |
| Total Graphics Power (TGP): | 220 W | 250 W |
|
Graphics Processor
|
||
| Compute Units: | 56 | 60 |
| Shading Units: | 3584 | 3840 |
| Texture Mapping Units (TMUs): | 224 | 240 |
| Render Output Units (ROPs): | 128 | 96 |
| Tensor Cores: | 112 | — |
| Ray Tracing Cores: | 56 | 60 |
| Base Clock: | 1330 | 1700 MHz |
| Boost Clock: | 2520 | 2105 MHz |
| L1 Cache: | 128 KB per cluster | 128 KB per Array |
| L2 Cache: | 8 MB | 4 MB |
| L3 Cache: | 64 MB | 128 MB |
|
Raw Performance
|
||
| Pixel Fill Rate: | 322.6 GPixel/s | 202.1 GPixel/s |
| Texture Fill Rate: | 564.5 GTexel/s | 505.2 GTexel/s |
| FP32 Performance: | 36.13 TFLOPs | 16.17 TFLOPs |
|
Memory
|
||
| Memory Type: | GDDR6 | GDDR6 |
| Memory Size: | 16 GB | 16 GB |
| Memory Bus Width: | 256-bit | 256-bit |
| Memory Clock: | 2518 | 2000 MHz |
| Effective Memory Speed: | 20100 | 16000 Mbps |
| Bandwidth: | 640 | 512.0 GB/s |
|
APIs
|
||
| DirectX: | 12 | 12.2 |
| Vulkan: | 1.3 | 1.4 |
| OpenGL: | 4.6 | 4.6 |
| OpenCL: | 2.2 | 2.1 |
| CUDA: | No | — |
| Ray Tracing: | Yes | Yes |
| DLSS: | No | — |
| FSR: | — | FSR |
| DisplayPort: | 2.1a | 1.4a |
| HDMI: | 2.1b | 2.1 |
|
Gaming FPS
|
||
| 1080p Ultra (FPS): | 180 | 129 |
| 1440p Ultra (FPS): | 139 | 95 |
| 4K Ultra (FPS): | 83 | 55 |
|
Benchmarks
|
||
|
3D Mark
|
||
| Steel Nomad Lite | 22669 | 14554 |
| Time Spy | 26923 | 16214 |
| Solar Bay | 105195 | 64675 |
| Port Royal | 16114 | 8129 |
| Fire Strike | 60172 | 44369 |
| Wild Life Extreme | 48175 | 29737 |
| Night Raid | 176602 | 142530 |
|
GeekBench 6 OpenCL
|
||
| Compute Score | 149949 | 135060 |
| Background Blur | 377.5 | 298.6 |
| Face Detection | 221.3 | 186.2 |
| Horizon Detection | 6.4 | 4.75 |
| Edge Detection | 8.99 | 6.68 |
| Gaussian Blur | 8.52 | 5.58 |
| Feature Matching | 1.36 | 1.16 |
| Stereo Matching | 606 | 579 |
| Particle Physics | 8521.2 | 18755.1 |
|
Passmark Graphics
|
||
| G3D Mark | 25420 | 22020 |
| G2D Mark | 1272 | 996 |
| DirectX 11 | 279 | 212 |
| DirectX 12 | 74 | 89 |
| GPU Compute | 14801 | 10775 |
|
GFXBench 5
|
||
| Aztec Ruins High (4K) | 274.70 | 219.60 |
| Aztec Ruins Normal | 1412.60 | 1131.00 |
| Car Chase | 1332.40 | 1005.00 |
| Manhattan 3.1.1 (1440p) | 1061.20 | 857.20 |
| T-Rex | 4127.00 | 3344.50 |
| Tessellation | 6097.50 | 2950.40 |
| ALU 2 | 7774.70 | 5114.60 |
| Driver Overhead 2 | 276.10 | 300.10 |
| API | OpenGL | OpenGL |
| OS | Windows | Windows |
|
Blender (Rendering)
|
||
| Blender Score | 2729 | 1888 |
|
GeekBench 6 ML
|
||
| Single Precision | 37056 | 25097 |
| Half Precision | 54866 | 27988 |
| Quantized | 29946 | 19116 |
| Image Classification | 15375 | 11245 |
| Image Segmentation | 37834 | 13617 |
| Image Super Resolution | 43910 | 27747 |
| Face Detection | 67858 | 38124 |
| Pose Estimation | 172939 | 119493 |
| Text Classification | 4469 | 2425 |
| Machine Translation | 8499 | 5228 |
| Object Detection | 15393 | 11986 |
| Depth Estimation | 66890 | 46083 |
| Style Transfer | 365633 | 281860 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
|
FurMark
|
||
| 1080p Vulkan | 17149 | 10943 |
| 1440p Vulkan | 12146 | 7598 |
| 2160p Vulkan | 5814 | 4055 |
| 1080p OpenGL | 17615 | 11926 |
| 1440p OpenGL | 11876 | 8292 |
| 2160p OpenGL | 5810 | 4416 |
Tip: ▲ indicates a higher-is-better spec advantage, while ▼ indicates a lower-is-better advantage.
PERFORMANCE CHART COMPARISON OF Radeon RX 9070 AND Radeon RX 6800
The charts below visualize how Radeon RX 9070 and Radeon RX 6800 stack up in key performance metrics.
Radar Chart Comparison
Bullet Chart Comparison
Value For Money Calculator
Prices use available launch or current data. Enter your own prices to see which GPU gives better value.
Radeon RX 9070
Radeon RX 6800
Calculating...
Domain Score Summary
Scores are generated by Comparigon's scoring algorithm and are intended as a high-level guide. They may not map 1-to-1 with the individual spec-by-spec comparisons shown in the table.
Our Verdict
In conclusion, the Radeon RX 9070 dominates overall compared to the Radeon RX 6800. It comes out ahead across every comparable key area.
Try to Compare Again One of These GPUs With Another GPU
Pick which GPU to keep, then search for the other GPU to compare.
Frequently Asked Questions about Radeon RX 9070 vs Radeon RX 6800
Radeon RX 9070 scores 66% higher than Radeon RX 6800 in 3DMark Time Spy (26,923 vs 16,214).
Radeon RX 9070 scores 98.2% higher than Radeon RX 6800 in 3DMark Port Royal (16,114 vs 8,129).
Radeon RX 9070 scores 11% higher than Radeon RX 6800 in Geekbench 6 OpenCL (149,949 vs 135,060).
Radeon RX 9070 and Radeon RX 6800 have the same listed graphics memory capacity (16 GB vs 16 GB).
Radeon RX 9070 has 25% higher memory bandwidth than Radeon RX 6800 (640 GB/s vs 512.0 GB/s).
Both list GDDR6 for memory type.
Radeon RX 9070 lists 220 W for graphics power, while Radeon RX 6800 lists 250 W for graphics power.
Radeon RX 9070 scores 44.5% higher than Radeon RX 6800 in Blender (2,729 vs 1,888).
Radeon RX 9070 lists PCIe 5.0 x16 for bus interface, while Radeon RX 6800 lists PCIe 4.0 x16 for bus interface.
Radeon RX 9070 was released on March 6, 2025. Radeon RX 6800 was released on October 28, 2020. Radeon RX 9070 was released 1590 days after Radeon RX 6800.
Disclaimer: Specs, pricing, and benchmarks are sourced from official manufacturer data and verified test results. While we strive for precision, product details and pricing may change. Comparigon may earn an affiliate commission on qualifying purchases.