GeForce RTX 4070 Ti SUPER VS GeForce RTX 3090 Ti
We are comparing the GeForce RTX 4070 Ti SUPER (NVIDIA) with the GeForce RTX 3090 Ti (NVIDIA). 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 4070 Ti SUPER AND GeForce RTX 3090 Ti
Here’s how GeForce RTX 4070 Ti SUPER and GeForce RTX 3090 Ti stack up against each other in their most impactful areas.
Reasons to consider the GeForce RTX 4070 Ti SUPER
-
5% higher 4K Ultra FPS (79 vs 75)
-
7% higher 1440p Ultra FPS (136 vs 127)
-
4% higher 1080p Ultra FPS (168 vs 162)
-
40% higher Boost Clock (2610 MHz vs 1860 MHz)
-
11% higher 3DMark Time Spy score (24223 vs 21851)
Reasons to consider the GeForce RTX 3090 Ti
-
50% more memory bandwidth (1008 GB/s vs 672.3 GB/s)
-
50% more VRAM (24GB vs 16GB)
-
50% higher Memory Bus Width (384 Bit vs 256 Bit)
-
1.3× higher Tensor Cores (336 vs 264)
-
1.3× higher Ray Tracing Cores (84 vs 66)
SPECIFICATION TABLE COMPARISON OF GeForce RTX 4070 Ti SUPER AND GeForce RTX 3090 Ti
Below is the detailed specification table comparing GeForce RTX 4070 Ti SUPER and GeForce RTX 3090 Ti.
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 4070 Ti SUPER | GeForce RTX 3090 Ti |
|---|---|---|
|
General Info
|
||
| GPU Name: | GeForce RTX 4070 Ti SUPER | GeForce RTX 3090 Ti |
| GPU Type: | Discrete | Discrete |
| Codename: | AD103 | GA102 |
| Vendor: | NVIDIA | NVIDIA |
| Foundry: | TSMC | Samsung |
| Architecture: | Ada Lovelace | Ampere |
| Generation: | GeForce 40 | GeForce 30 |
| Release Date: | January 8, 2024 | January 27, 2022 |
|
Board Design
|
||
| Bus Interface: | PCIe 4.0 x16 | PCIe 4.0 x16 |
| PCIe Version: | 4.0 | 4.0 |
| PCIe Lanes: | x16 | x16 |
| Process Size: | 5 nm | 8 nm |
| Transistors: | 45.9 billion | 28.3 billion |
| Density: | 121.1 MTr/mm² | 45.1 MTr/mm² |
| Die Size: | 379 mm² | 628 mm² |
| Board Length: | 310 mm | 336 mm |
| Board Width: | 61 mm | 61 mm |
| Board Height: | 140 mm | 140 mm |
| Total Graphics Power (TGP): | 285 W | 450 W |
|
Graphics Processor
|
||
| Compute Units: | 66 | 84 |
| Shading Units: | 8448 | 10752 |
| Texture Mapping Units (TMUs): | 264 | 336 |
| Render Output Units (ROPs): | 96 | 112 |
| Tensor Cores: | 264 | 336 |
| Ray Tracing Cores: | 66 | 84 |
| Base Clock: | 2340 MHz | 1560 MHz |
| Boost Clock: | 2610 MHz | 1860 MHz |
| L1 Cache: | 128 KB per SM | 128 KB per SM |
| L2 Cache: | 48 MB | 6 MB |
|
Raw Performance
|
||
| Pixel Fill Rate: | 250.6 GPixel/s | 208.3 GPixel/s |
| Texture Fill Rate: | 689.0 GTexel/s | 625.0 GTexel/s |
| FP32 Performance: | 44.10 TFLOPs | 40.00 TFLOPs |
|
Memory
|
||
| Memory Type: | GDDR6X | GDDR6X |
| Memory Size: | 16 GB | 24 GB |
| Memory Bus Width: | 256-bit | 384-bit |
| Memory Clock: | 1313 MHz | 1313 MHz |
| Effective Memory Speed: | 21000 Mbps | 21000 Mbps |
| Bandwidth: | 672.3 GB/s | 1008 GB/s |
|
APIs
|
||
| DirectX: | 12.2 | 12.2 |
| Vulkan: | 1.4 | 1.4 |
| OpenGL: | 4.6 | 4.6 |
| OpenCL: | 3.0 | 3.0 |
| CUDA: | 8.9 | 8.6 |
| Ray Tracing: | Yes | Yes |
| DLSS: | DLSS 3 | DLSS 2 |
| DisplayPort: | 1.4a | 1.4a |
| HDMI: | 2.1 | 2.1 |
|
Gaming FPS
|
||
| 1080p Ultra (FPS): | 168 | 162 |
| 1440p Ultra (FPS): | 136 | 127 |
| 4K Ultra (FPS): | 79 | 75 |
|
Benchmarks
|
||
|
3D Mark
|
||
| Steel Nomad Lite | 25722 | 24355 |
| Time Spy | 24223 | 21851 |
| Solar Bay | 116467 | 109181 |
| Port Royal | 15792 | 14889 |
| Fire Strike | 56335 | 51956 |
| Wild Life Extreme | 49906 | 48863 |
| Night Raid | 176372 | 156306 |
|
GeekBench 6 OpenCL
|
||
| Compute Score | 237068 | 232083 |
| Background Blur | 331.7 | 362.7 |
| Face Detection | 211.6 | 227.9 |
| Horizon Detection | 9.63 | 11.3 |
| Edge Detection | 13.7 | 15.9 |
| Gaussian Blur | 13.9 | 12.1 |
| Feature Matching | 2.15 | 1.56 |
| Stereo Matching | 1210 | 1080 |
| Particle Physics | 33566 | 31024.6 |
|
Passmark Graphics
|
||
| G3D Mark | 31815 | 29340 |
| G2D Mark | 1240 | 1228 |
| DirectX 11 | 278 | 239 |
| DirectX 12 | 119 | 122 |
| GPU Compute | 18298 | 16657 |
|
GFXBench 5
|
||
| Aztec Ruins High (4K) | 277.50 | 249.00 |
| Aztec Ruins Normal | 1300.60 | 1005.10 |
| Car Chase | 1119.60 | 897.20 |
| Manhattan 3.1.1 (1440p) | 943.40 | 781.70 |
| T-Rex | 4724.80 | 4109.90 |
| Tessellation | 8597.70 | 7000.80 |
| ALU 2 | 8528.70 | 7102.50 |
| Driver Overhead 2 | 289.10 | 274.90 |
| API | OpenGL | OpenGL |
| OS | Windows | Windows |
|
Blender (Rendering)
|
||
| Blender Score | 7087 | 6098 |
|
GeekBench 6 ML
|
||
| Single Precision | 32793 | 26701 |
| Half Precision | 47412 | 38573 |
| Quantized | 24566 | 15995 |
| Image Classification | 12970 | 10246 |
| Image Segmentation | 26364 | 22830 |
| Image Super Resolution | 37217 | 23532 |
| Face Detection | 58720 | 48657 |
| Pose Estimation | 177604 | 147241 |
| Text Classification | 3815 | 2917 |
| Machine Translation | 5829 | 4427 |
| Object Detection | 15675 | 13323 |
| Depth Estimation | 62447 | 40055 |
| Style Transfer | 357918 | 298683 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
|
FurMark
|
||
| 1080p Vulkan | 17225 | 14720 |
| 1440p Vulkan | 12186 | 9754 |
| 2160p Vulkan | 5819 | 5128 |
| 1080p OpenGL | 16349 | 15145 |
| 1440p OpenGL | 12412 | 9990 |
| 2160p OpenGL | 6265 | 5442 |
Tip: ▲ indicates a higher-is-better spec advantage, while ▼ indicates a lower-is-better advantage.
PERFORMANCE CHART COMPARISON OF GeForce RTX 4070 Ti SUPER AND GeForce RTX 3090 Ti
The charts below visualize how GeForce RTX 4070 Ti SUPER and GeForce RTX 3090 Ti 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 4070 Ti SUPER
GeForce RTX 3090 Ti
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 GeForce RTX 4070 Ti SUPER dominates overall compared to the GeForce RTX 3090 Ti. 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 GeForce RTX 4070 Ti SUPER vs GeForce RTX 3090 Ti
GeForce RTX 4070 Ti SUPER scores 10.9% higher than GeForce RTX 3090 Ti in 3DMark Time Spy (24,223 vs 21,851).
GeForce RTX 4070 Ti SUPER scores 6.1% higher than GeForce RTX 3090 Ti in 3DMark Port Royal (15,792 vs 14,889).
GeForce RTX 4070 Ti SUPER scores 2.1% higher than GeForce RTX 3090 Ti in Geekbench 6 OpenCL (237,068 vs 232,083).
GeForce RTX 3090 Ti has 50% more graphics memory than GeForce RTX 4070 Ti SUPER (24 GB vs 16 GB).
GeForce RTX 3090 Ti has 49.9% higher memory bandwidth than GeForce RTX 4070 Ti SUPER (1008 GB/s vs 672.3 GB/s).
Both list GDDR6X for memory type.
GeForce RTX 4070 Ti SUPER lists 285 W for graphics power, while GeForce RTX 3090 Ti lists 450 W for graphics power.
GeForce RTX 4070 Ti SUPER scores 16.2% higher than GeForce RTX 3090 Ti in Blender (7,087 vs 6,098).
Both list PCIe 4.0 x16 for bus interface.
GeForce RTX 4070 Ti SUPER was released on January 8, 2024. GeForce RTX 3090 Ti was released on January 27, 2022. GeForce RTX 4070 Ti SUPER was released 711 days after GeForce RTX 3090 Ti.
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.