GeForce RTX 3090 VS Radeon RX 9070 XT
We are comparing the GeForce RTX 3090 (NVIDIA) with the Radeon RX 9070 XT (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 GeForce RTX 3090 AND Radeon RX 9070 XT
Here’s how GeForce RTX 3090 and Radeon RX 9070 XT stack up against each other in their most impactful areas.
Reasons to consider the GeForce RTX 3090
-
16% higher Geekbench 6 OpenCL score (211669 vs 182816)
-
88% higher Blender score (5864 vs 3116)
-
46% more memory bandwidth (936.2 GB/s vs 640 GB/s)
-
50% more VRAM (24GB vs 16GB)
-
50% higher Memory Bus Width (384 Bit vs 256 Bit)
Reasons to consider the Radeon RX 9070 XT
-
29% higher 4K Ultra FPS (89 vs 69)
-
27% higher 1440p Ultra FPS (151 vs 119)
-
27% higher 1080p Ultra FPS (193 vs 152)
-
75% higher Boost Clock (2970 MHz vs 1695 MHz)
-
50% higher 3DMark Time Spy score (29803 vs 19898)
SPECIFICATION TABLE COMPARISON OF GeForce RTX 3090 AND Radeon RX 9070 XT
Below is the detailed specification table comparing GeForce RTX 3090 and Radeon RX 9070 XT.
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 | GeForce RTX 3090 | Radeon RX 9070 XT |
|---|---|---|
|
General Info
|
||
| GPU Name: | GeForce RTX 3090 | Radeon RX 9070 XT |
| GPU Type: | Discrete | Discrete |
| Codename: | GA102 | — |
| Vendor: | NVIDIA | AMD |
| Foundry: | Samsung | TSMC |
| Architecture: | Ampere | RDNA 4.0 |
| Generation: | GeForce 30 | Navi IV (RX 9000) |
| Release Date: | September 1, 2020 | March 6, 2025 |
|
Board Design
|
||
| Bus Interface: | PCIe 4.0 x16 | PCIe 5.0 x16 |
| PCIe Version: | 4.0 | 5.0 |
| PCIe Lanes: | x16 | x16 |
| Process Size: | 8 nm | 4 nm |
| Transistors: | 28.3 billion | 53.9 billion |
| Density: | 45.1 MTr/mm² | 151.19 MTr/mm² |
| Die Size: | 628 mm² | 356.5 |
| Board Length: | 336 mm | — |
| Board Width: | 61 mm | — |
| Board Height: | 140 mm | — |
| Total Graphics Power (TGP): | 350 W | 304 W |
|
Graphics Processor
|
||
| Compute Units: | 82 | 64 |
| Shading Units: | 10496 | 4096 |
| Texture Mapping Units (TMUs): | 328 | 256 |
| Render Output Units (ROPs): | 112 | 128 |
| Tensor Cores: | 328 | 128 |
| Ray Tracing Cores: | 82 | 64 |
| Base Clock: | 1395 MHz | 1660 |
| Boost Clock: | 1695 MHz | 2970 |
| L1 Cache: | 128 KB per SM | 128KB per cluster |
| L2 Cache: | 6 MB | 4MB shared |
|
Raw Performance
|
||
| Pixel Fill Rate: | 189.8 GPixel/s | 380.2 GPixel/s |
| Texture Fill Rate: | 556.0 GTexel/s | 760.3 GTexel/s |
| FP32 Performance: | 35.58 TFLOPs | 48.66 TFLOPs |
|
Memory
|
||
| Memory Type: | GDDR6X | GDDR6 |
| Memory Size: | 24 GB | 16 GB |
| Memory Bus Width: | 384-bit | 256-bit |
| Memory Clock: | 1219 MHz | 2518 |
| Effective Memory Speed: | 19500 Mbps | 20100 |
| Bandwidth: | 936.2 GB/s | 640 |
|
APIs
|
||
| DirectX: | 12.2 | 12.2 |
| Vulkan: | 1.4 | 1.3 |
| OpenGL: | 4.6 | 4.6 |
| OpenCL: | 3.0 | 2.2 |
| CUDA: | 8.6 | No |
| Ray Tracing: | Yes | Yes |
| DLSS: | DLSS 2 | No |
| DisplayPort: | 1.4a | 2.1a |
| HDMI: | 2.1 | — |
|
Gaming FPS
|
||
| 1080p Ultra (FPS): | 152 | 193 |
| 1440p Ultra (FPS): | 119 | 151 |
| 4K Ultra (FPS): | 69 | 89 |
|
Benchmarks
|
||
|
3D Mark
|
||
| Steel Nomad Lite | 21870 | 26116 |
| Time Spy | 19898 | 29803 |
| Solar Bay | 97359 | 120093 |
| Port Royal | 13633 | 18556 |
| Fire Strike | 47513 | 66408 |
| Wild Life Extreme | 43662 | 54361 |
| Night Raid | 139745 | 196877 |
|
GeekBench 6 OpenCL
|
||
| Compute Score | 211669 | 182816 |
| Background Blur | 320.8 | 427.4 img/sec |
| Face Detection | 207.2 | 251 img/sec |
| Horizon Detection | 10.1 | 6.77 Gpixels/sec |
| Edge Detection | 14.4 | 9.42 Gpixels/sec |
| Gaussian Blur | 11.5 | 9.35 Gpixels/sec |
| Feature Matching | 1.48 | 1.42 Gpixels/sec |
| Stereo Matching | 984.2 | 651.4 Gpixels/sec |
| Particle Physics | 27764.9 | 23630 FPS |
|
Passmark Graphics
|
||
| G3D Mark | 26570 | 26866 |
| G2D Mark | 1069 | 1320 |
| DirectX 11 | 219 | 294 |
| DirectX 12 | 110 | 77 |
| GPU Compute | 15155 | 15958 Ops/s |
|
GFXBench 5
|
||
| Aztec Ruins High (4K) | 247.50 | 313.30 |
| Aztec Ruins Normal | 978.40 | 1794.90 |
| Car Chase | 854.10 | 1498.00 |
| Manhattan 3.1.1 (1440p) | 747.40 | 1199.30 |
| T-Rex | 3732.10 | 5080.10 |
| Tessellation | 6622.80 | 6928.50 |
| ALU 2 | 6650.90 | 9196.70 |
| Driver Overhead 2 | 296.00 | 339.10 |
| API | OpenGL | OpenGL |
| OS | Windows | Windows |
|
Blender (Rendering)
|
||
| Blender Score | 5864 | 3116 |
|
GeekBench 6 ML
|
||
| Single Precision | 27237 | 39190 |
| Half Precision | 41500 | 55727 |
| Quantized | 15927 | 33599 |
| Image Classification | 10665 | 18001 |
| Image Segmentation | 28963 | 25174 |
| Image Super Resolution | 22697 | 45714 |
| Face Detection | 55232 | 74776 |
| Pose Estimation | 128155 | 196137 |
| Text Classification | 3152 | 5163 |
| Machine Translation | 5088 | 8677 |
| Object Detection | 13891 | 19602 |
| Depth Estimation | 37984 | 74879 |
| Style Transfer | 272000 | 411302 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
|
FurMark
|
||
| 1080p Vulkan | 11604 | 19161 |
| 1440p Vulkan | 8504 | 14200 |
| 2160p Vulkan | 4684 | 7713 |
| 1080p OpenGL | 11467 | 20135 |
| 1440p OpenGL | 8557 | 14412 |
| 2160p OpenGL | 4804 | 7754 |
Tip: ▲ indicates a higher-is-better spec advantage, while ▼ indicates a lower-is-better advantage.
PERFORMANCE CHART COMPARISON OF GeForce RTX 3090 AND Radeon RX 9070 XT
The charts below visualize how GeForce RTX 3090 and Radeon RX 9070 XT 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.
GeForce RTX 3090
Radeon RX 9070 XT
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 XT dominates overall compared to the GeForce RTX 3090. Its strongest advantages are in Gaming Performance, AI & Machine Learning, Hardware Architecture and Energy Efficiency. The GeForce RTX 3090 is the better fit if your top priority is Workstation.
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 GeForce RTX 3090 vs Radeon RX 9070 XT
Radeon RX 9070 XT scores 49.8% higher than GeForce RTX 3090 in 3DMark Time Spy (29,803 vs 19,898).
Radeon RX 9070 XT scores 36.1% higher than GeForce RTX 3090 in 3DMark Port Royal (18,556 vs 13,633).
GeForce RTX 3090 scores 15.8% higher than Radeon RX 9070 XT in Geekbench 6 OpenCL (211,669 vs 182,816).
GeForce RTX 3090 has 50% more graphics memory than Radeon RX 9070 XT (24 GB vs 16 GB).
GeForce RTX 3090 has 46.3% higher memory bandwidth than Radeon RX 9070 XT (936.2 GB/s vs 640 GB/s).
GeForce RTX 3090 lists GDDR6X for memory type, while Radeon RX 9070 XT lists GDDR6 for memory type.
GeForce RTX 3090 lists 350 W for graphics power, while Radeon RX 9070 XT lists 304 W for graphics power.
GeForce RTX 3090 scores 88.2% higher than Radeon RX 9070 XT in Blender (5,864 vs 3,116).
GeForce RTX 3090 lists PCIe 4.0 x16 for bus interface, while Radeon RX 9070 XT lists PCIe 5.0 x16 for bus interface.
GeForce RTX 3090 was released on September 1, 2020. Radeon RX 9070 XT was released on March 6, 2025. Radeon RX 9070 XT was released 1647 days after GeForce RTX 3090.
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.