NVIDIA GeForce RTX 4070 SUPER vs NVIDIA GeForce RTX 3090
The GeForce RTX 4070 SUPER has 11% better performance than the GeForce RTX 3090 for the 3DMark 11 Performance GPU benchmark.
The GeForce RTX 4070 SUPER has 178% better value for the money than the GeForce RTX 3090 for the 3DMark 11 Performance GPU benchmark.
Summary
About the NVIDIA GeForce RTX 4070 SUPER GPU
The GeForce RTX 4070 SUPER is a desktop graphics card by NVIDIA. It launched in Q1 2024 with a suggested retail price of $599. Its AD104 chip that powers the GPU uses the Ada Lovelace architecture and is fabricated on the 5 nm process.
This GPU is paired with 12 GB of GDDR6X VRAM. Its 1,313 MHz memory clock and 192 bit interface gives it a bandwidth of 504.2 Gb/s. This impacts how much data it can store, and how fast it transfers the data to and from memory.
The RTX 4070 SUPER is a dual slot graphics card, taking up 2 PCIe slots. It supports 1x HDMI 2.1, 3x DisplayPort 1.4a display ports. This desktop card has a TDP of 220 W. NVIDIA recommends using a power supply of at least 550 W with this card. A power supply lower than this might result in system crashes and potentially damage your hardware.
The GeForce RTX 4070 SUPER has the 11th highest 3DMark 11 Performance GPU score among the 540 benchmarked GPUs in our database. It achieves 65.16% of the performance of the best benchmarked GPU, the NVIDIA GeForce RTX 4090. Its 68,373 score and $599 launch price (MSRP) gives it a performance per dollar of 114.15. This is the 11th best in value for the 3DMark 11 Performance GPU benchmark.
About the NVIDIA GeForce RTX 3090 GPU
The GeForce RTX 3090 is a desktop graphics card by NVIDIA. It launched in Q3 2020 with a suggested retail price of $1,499. Its GA102 chip that powers the GPU uses the Ampere architecture and is fabricated on the 8 nm process.
This GPU is paired with 24 GB of GDDR6X VRAM. Its 1,219 MHz memory clock and 384 bit interface gives it a bandwidth of 936.2 Gb/s. This impacts how much data it can store, and how fast it transfers the data to and from memory.
The RTX 3090 is a large graphics card, taking up 3 PCIe slots. It supports HDMI 2.1, DisplayPort 1.4a display ports. This desktop card has a TDP of 350 W. NVIDIA recommends using a power supply of at least 750 W with this card. A power supply lower than this might result in system crashes and potentially damage your hardware.
The GeForce RTX 3090 has the 15th highest 3DMark 11 Performance GPU score among the 540 benchmarked GPUs in our database. It achieves 58.62% of the performance of the best benchmarked GPU, the NVIDIA GeForce RTX 4090. Its 61,518 score and $1,499 launch price (MSRP) gives it a performance per dollar of 41.04. This is the 69th best in value for the 3DMark 11 Performance GPU benchmark.
General Info
General overview of the GPU, including details like its manufacturer, release date, launch price, and current production status.
| Info | GeForce RTX 4070 SUPER | GeForce RTX 3090 |
|---|---|---|
| Manufacturer | NVIDIA | NVIDIA |
| Architecture | Ada Lovelace | Ampere |
| Market Segment | Desktop | Desktop |
| Release Date | Q1 2024 | Q3 2020 |
| Launch Price (MSRP) | $599 | $1,499 |
| Production Status | Active | Active |
| Shop | Check Price | Check Price |
Gaming Performance
Select a game to compare FPS metrics
FPS Benchmarks
This table showcases the average frame rate (FPS) achieved both GPUs in at various resolutions. Frame rate is a crucial indicator of how smoothly the GPU can run the game. A higher FPS generally translates to a smoother gameplay experience.
- Frames Per Second
F1 24 | GeForce RTX 4070 SUPER | GeForce RTX 3090 |
|---|---|---|
| Low - 1080p | -- | 498 FPS |
| Medium - 1080p | -- | 446 FPS |
| High - 1080p | -- | 340 FPS |
| Ultra - 1080p | -- | 118 FPS |
| QHD - 1440p | -- | 79 FPS |
| 4K UHD - 2160p | -- | 41 FPS |
Compare Frames Per Second (FPS)
The average frame rate (FPS) in can be compared to similar GPUs to assess relative performance. Generally, higher FPS results in a smoother gameplay experience.
| GPU | Frames Per Second | |
|---|---|---|
| GeForce RTX 4080 | 55 | +36% |
| Radeon RX 7900 XTX | 46.6 | +15% |
| GeForce RTX 3090 | 40.5 | |
| Radeon RX 7900 XT | 37 | -9% |
| Radeon RX 6950 XT | 30.2 | -25% |
| Radeon RX 7800 XT | 28.7 | -29% |
| GeForce RTX 3070 Ti | 28.2 | -30% |
| GeForce RTX 3060 Ti | 22.2 | -45% |
| Arc A770 | 21.2 | -48% |
Compare Cost Per Frame
The average cost per frame in can be compared to similar GPUs to assess relative value. Generally, a lower cost per frame implies better value for your money.
| GPU | Cost Per Frame | |
|---|---|---|
| GeForce RTX 4080 | 21.8 | -41% |
| Radeon RX 7900 XT | 24.3 | -34% |
| Radeon RX 6800 | 28.11 | -24% |
| Radeon RX 6950 XT | 36.39 | -2% |
| GeForce RTX 3090 | 37.01 | |
Benchmark Performance
The GeForce RTX 4070 SUPER has 11% better performance than the GeForce RTX 3090 for the 3DMark 11 Performance GPU benchmark.
The GeForce RTX 4070 SUPER is ranked 11th with a score of 68,373, and the GeForce RTX 3090 is ranked 15th with a score of 61,518.
The GeForce RTX 4070 SUPER has 178% better value for the money than the GeForce RTX 3090 for the 3DMark 11 Performance GPU benchmark.
The GeForce RTX 4070 SUPER is ranked 11th with a performance per dollar of 114.15, and the GeForce RTX 3090 is ranked 69th with a performance per dollar of 41.04.
Relative Performance
The average score in the benchmark test can be compared to similar GPUs to assess relative performance. Generally, powerful GPUs tend to have higher scores.
| GPU | Benchmark Performance | |
|---|---|---|
| GeForce RTX 4070 Ti | 75,612 | +11% |
| GeForce RTX 4070 Ti SUPER | 74,834 | +9% |
| Radeon RX 6950 XT | 72,227.5 | +6% |
| GeForce RTX 3090 Ti | 69,481 | +2% |
| GeForce RTX 4070 SUPER | 68,373 | |
| Radeon RX 7800 XT | 65,610.5 | -4% |
| GeForce RTX 3090 | 61,518 | -10% |
| GeForce RTX 3080 Ti | 60,980 | -11% |
| GeForce RTX 4070 | 59,969 | -12% |
| Radeon RX 6900 XT | 59,119 | -14% |
Relative Value For Money
The average performance per dollar in the benchmark test can be compared to similar GPUs to assess relative value. A higher score implies a better value for your money.
| GPU | Performance Per Dollar | |
|---|---|---|
| Arc A770 | 125.54 | +10% |
| GeForce RTX 4060 Ti (8 GB) | 119.81 | +5% |
| GeForce RTX 4070 SUPER | 114.15 | |
| Radeon RX 6600 XT | 103.04 | -10% |
| GeForce RTX 4070 | 100.12 | -12% |
| GeForce RTX 3080 Ti | 50.86 | -55% |
| GeForce RTX 2080 Ti | 47.21 | -59% |
| GeForce RTX 3090 | 41.04 | -64% |
| GeForce RTX 3090 Ti | 34.76 | -70% |
Benchmark Scores
This table showcases the average performance scores achieved by both GPUs across industry-standard benchmark tests. These scores provide a valuable insight into overall performance. Powerful GPUs tend to have higher scores.
- Popular
| Benchmark | GeForce RTX 4070 SUPER | GeForce RTX 3090 |
|---|---|---|
| 3DMark Time Spy Graphics | 20,992 (+9.34%) | 19,198 |
| 3DMark Time Spy Score | 21,186 (+13.06%) | 18,739 |
| 3DMark Cloud Gate Graphics | 171,098 | 231,612 (+35.37%) |
| 3DMark Fire Strike Standard Graphics | 48,876 (+3.46%) | 47,241 |
| 3DMark Night Raid Graphics | 198,556 (+38.93%) | 142,919 |
| 3DMark 11 Performance Score | 51,339.5 (+7.19%) | 47,895 |
| Cinebench R15 OpenGL 64 Bit | -- | 368 |
| PassMark G3D Mark | 29,997 (+11.95%) | 26,795 |
| PassMark G2D Mark | 1,143 (+8.55%) | 1,053 |
Technical Specs
Graphics Processor
General information about the graphics processing unit like their architecture, manufacturing process size, and transistor count. Newer GPU architectures generally bring efficiency improvements and may introduce technologies that enhance graphical capabilities.
| Spec | GeForce RTX 4070 SUPER | GeForce RTX 3090 |
|---|---|---|
| Codename | AD104 | GA102 |
| Architecture | Ada Lovelace | Ampere |
| Process Size | 5 nm | 8 nm |
| Transistors | 35,800 million | 28,300 million |
Memory Details
Memory specifications like their capacity, bandwidth, and clock speeds. GPU memory stores graphics data like frames, textures, and shadows which helps display rendered images. These specs are crucial for graphics-intense applications like gaming and 3D modeling.
| Spec | GeForce RTX 4070 SUPER | GeForce RTX 3090 |
|---|---|---|
| Memory Size | 12 GB | 24 GB |
| Memory Type | GDDR6X | GDDR6X |
| Memory Bandwidth | 504.2 Gb/s | 936.2 Gb/s |
| Memory Clock | 1,313 MHz | 1,219 MHz |
| Memory Interface | 192 bit | 384 bit |
| L1 Cache | 128 KB | 128 KB |
| L2 Cache | 48 MB | 6 MB |
Board Compatibility
Compatibility information like their slot size, bus interface, power consumption, and display support. These specs are useful for verifying compatibility with your motherboard, power supply, and monitor.
| Spec | GeForce RTX 4070 SUPER | GeForce RTX 3090 |
|---|---|---|
| Slots | 2 slots | 3 slots |
| Bus Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| Thermal Design Power (TDP) | 220 W | 350 W |
| Suggested PSU | 550 W | 750 W |
| Power Connectors | 1x 16-pin | 1x 12-pin |
| Outputs | 1x HDMI 2.1, 3x DisplayPort 1.4a | HDMI 2.1, DisplayPort 1.4a |
Cores & Clock Speeds
Processing power information like its cores and clock speed. These specs impact how fast they can process graphics. Each type of core or component serves a specific computational purpose.
| Spec | GeForce RTX 4070 SUPER | GeForce RTX 3090 |
|---|---|---|
| CUDA Cores | 7,168 | 10,496 |
| Stream Multiprocessors (SM) | 56 | 82 |
| Texture Mapping Units (TMU) | 224 | 328 |
| Render Output Units (ROP) | 80 | 112 |
| Tensor Cores | 224 | 328 |
| Ray Tracing Cores | 56 | 82 |
| Core Clock Speed | 1,980 MHz | 1,395 MHz |
| Core Clock Speed (Boost) | 2,475 MHz | 1,695 MHz |
Theoretical Performance
Theoretical performance numbers derived from the raw specifications of the different components like core count and clock speeds. While these provide a glimpse into peak processing power, they do not represent real-world performance.
| Spec | GeForce RTX 4070 SUPER | GeForce RTX 3090 |
|---|---|---|
| Pixel Fill Rate | 198 GPixel/s | 189.8 GPixel/s |
| Texture Fill Rate | 554.4 GTexel/s | 556 GTexel/s |
| FP32 Performance | 35.48 TFLOPS | 35.58 TFLOPS |
| FP64 Performance | 554.4 GFLOPS | 556 GFLOPS |
API Support
Graphics API versions supported by these graphics cards. APIs evolve over time, introducing new features and functionalities. Older GPUs may not support recent versions.
| Spec | GeForce RTX 4070 SUPER | GeForce RTX 3090 |
|---|---|---|
| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
| OpenCL | 3.0 | 3.0 |
| OpenGL | 4.6 | 4.6 |
| Shader Model | 6.7 | 6.7 |
Check out these comparisons for similar GPUs:
Looking for alternatives? Check out these similar GPUs:
* Performance rating, performance per dollar, and rankings are based on the 3DMark 11 Performance GPU benchmark and MSRP.