GeForce RTX 4070 SUPER
NVIDIA
G3D Mark
29,958
MSRP
$599
AVG Price
$600
Performance Spectrum - GPU
About G3D Mark
G3D Mark is a standard benchmark that measures graphics performance in real-world gaming scenarios. It simplifies comparing cards from different brands, where higher scores directly correlate with better fps and smoother gaming experiences.
Overview
The GeForce RTX 4070 SUPER is manufactured by NVIDIA. It was released in January 8 2024. It features the Ada Lovelace architecture. The core clock ranges from 1980 MHz to 2475 MHz. It has 7168 shading units. The thermal design power (TDP) is 220W. Manufactured using 5 nm process technology. It features 56 dedicated ray tracing cores for enhanced lighting effects. G3D Mark benchmark score: 29,958 points. Launch price was $599.
Value Upgrade Path
This is the official ChipVERSUS Value Rating, comparing raw performance (G3D Mark) per dollar. Components placed above yours deliver better value for money.
Avg price is the current average price collected from markets across the web.
Performance Per Dollar GeForce RTX 4070 SUPER
FPS Benchmarks
Predicted performance for GeForce RTX 4070 SUPER across popular games. Tested paired with Ryzen 7 7800X3D to isolate GPU performance.
Among Us
Apex Legends
Counter-Strike 2
Cyberpunk 2077
Deadlock
Delta Force
Grand Theft Auto V
League of Legends
Minecraft
Palworld
Technical Analysis
Detailed breakdown of GeForce RTX 4070 SUPER specifications and capabilities.
Graphics Performance
The GeForce RTX 4070 SUPER scores 29,958 in the G3D Mark benchmark (the standard measure of rasterization GPU performance), placing it in the Enthusiast tier as a Recent generation graphics card. It is built on the Ada Lovelace (2022−2024) architecture (codename: AD104), manufactured on a 5 nm process— smaller process nodes improve power efficiency and transistor density. It packs 7168 shader units (the primary compute units for rendering pixels), 224 TMUs (texture mapping units), and 80 ROPs (render output units that handle final pixel output). Raw FP32 compute power: 35.48 TFLOPS — this measures the theoretical peak floating-point performance. Boost clock reaches 2475 MHz from a base of 1980 MHz.
| Specification | GeForce RTX 4070 SUPER |
|---|---|
| G3D MarkPassMark 3D graphics benchmark score | 29,958 |
| ArchitectureGPU microarchitecture generation | Ada Lovelace (2022−2024) |
| CodenameInternal GPU die codename | AD104 |
| Manufacturing ProcessFabrication node — smaller = more efficient | 5 nm |
| Shader UnitsCore compute units for rendering/compute | 7168 |
| TMUsTexture Mapping Units — handle texture sampling | 224 |
| ROPsRender Output Units — final pixel/color blending | 80 |
| Boost ClockMaximum GPU frequency under load | 2475 MHz |
| Base ClockGuaranteed minimum GPU frequency | 1980 MHz |
| Compute (FP32)Peak single-precision floating-point performance | 35.48 TFLOPS |
| Texture Fill RateTextures processed per second | 554.4 GTexel/s |
| PCIe InterfaceCPU↔GPU data link generation | PCIe 4.0 x16 |
| Transistor Count | 35,800 million |
| Performance RankPosition in global GPU performance ranking | #18 |
Video Memory (VRAM)
The GeForce RTX 4070 SUPER is equipped with 12 GB of GDDR6X video memory connected via a 192-bit memory bus, delivering 504 GB/s of bandwidth. GDDR6X offers higher data rates than standard GDDR6, reducing bottlenecks at high resolutions.
| Specification | GeForce RTX 4070 SUPER |
|---|---|
| VRAM SizeVideo memory capacity — more = better for high-res textures | 12 GB |
| VRAM TypeMemory technology generation | GDDR6X |
| Memory BusWidth of data path — wider = more bandwidth | 192-bit |
| BandwidthMaximum data throughput between GPU and VRAM | 504 GB/s |
| L1 Cache | 7 MB |
| L2 Cache | 48 MB |
Advanced Features & APIs
The GeForce RTX 4070 SUPER supports modern upscaling and frame generation technologies: NVIDIA Reflex, DLSS Frame Generation, DLSS Super Resolution — these can dramatically boost effective FPS by generating intermediate frames or upscaling from lower internal resolution. Graphics API support: DirectX 12 Ultimate, Vulkan 1.3, OpenGL 4.6— latest API versions enable the most advanced rendering features like ray tracing and mesh shaders.
| Specification | GeForce RTX 4070 SUPER |
|---|---|
| NVIDIA Reflex | ✅ Supported |
| DLSS Frame Generation | ✅ Supported |
| DLSS Super Resolution | ✅ Supported |
| DirectXMicrosoft graphics API version | 12 Ultimate |
| VulkanCross-platform graphics API | 1.3 |
| OpenGLLegacy graphics API | 4.6 |
| Compute APIGPGPU framework (CUDA/ROCm/OpenCL) | CUDA 8.9 |
Display & Media
Display outputs: 1x HDMI 2.1a, 3x DisplayPort 1.4a — supports up to 4 simultaneous displays. Hardware encoder: NVENC 8th gen, decoder: NVDEC 5th gen— dedicated hardware for video encoding/decoding accelerates streaming, recording, and video playback. Supported codecs: AV1,H.264,H.265/HEVC.
| Specification | GeForce RTX 4070 SUPER |
|---|---|
| HDMI 2.1a PortsNumber of HDMI 2.1a display connectors | 1x |
| DisplayPort 1.4a PortsNumber of DisplayPort 1.4a display connectors | 3x |
| Max DisplaysMaximum simultaneously connected monitors | 4 |
| Hardware EncoderVideo encoding engine version | NVENC 8th gen |
| Hardware DecoderVideo decoding engine version | NVDEC 5th gen |
| CodecsSupported video compression formats | AV1,H.264,H.265/HEVC |
Power & Dimensions
The GeForce RTX 4070 SUPER draws 220 Watt under load (TDP) — a 650W PSU minimum is recommended. Power connector: 16-pin (12VHPWR). Physical size: 245mm long, 111mm tall, occupying 2 expansion slots, weighing 1025g— verify your case has clearance before purchasing. Typical temperatures: 48°C at idle, 70°C under load.
| Specification | GeForce RTX 4070 SUPER |
|---|---|
| TDPPower consumption under load | 220 Watt |
| Recommended PSUMinimum power supply wattage | 650W |
| Power ConnectorRequired PCIe power cable type | 16-pin (12VHPWR) |
| Card LengthGPU card length — check case clearance | 245mm |
| Card Height | 111mm |
| Slot WidthExpansion slots occupied | 2-slot |
| Weight | 1025g |
| Idle TemperatureTypical temperature at desktop idle | 48°C |
| Load TemperatureTypical temperature under gaming load | 70°C |
Value Analysis
At an average price of $600 (MSRP: $599), the GeForce RTX 4070 SUPER delivers 50 G3D Mark points per dollar. Overall performance ranking position: #18 among all indexed GPUs.
| Specification | GeForce RTX 4070 SUPER |
|---|---|
| MSRPManufacturer's Suggested Retail Price | $599 |
| Avg Price (30d)Average market price over the last 30 days | $600 |
| Performance RankPosition in global GPU performance ranking | #18 |
| Release Date | January 8 2024 |
| Release Year | 2024 |
Specifications Reference
Raw spec sheet for quick lookup. The analysis cards above explain what these fields mean in practice.
2 categories
Technical Specifications
20 specs
Technical Specifications
20 specs
| ROPs | 80 |
| TMUs | 224 |
| Vram | 12 GB |
| L1 Cache | 7 MB |
| L2 Cache | 48 MB |
| Core Clock | 1980 MHz |
| Boost Clock | 2475 MHz |
| Memory Type | GDDR6X |
| Tensor Cores | 224 |
| Shading Units | 7168 |
| PCIe Generation | PCIe 4.0 x16 |
| Memory Bandwidth | 504 GB/s |
| Memory Bus Width | 192-bit |
| Transistor Count | 35,800 million |
| Frame Generation | NVIDIA Reflex: Yes | DLSS Frame Generation: Yes | DLSS Super Resolution: Yes |
| Ray Tracing Cores | 56 |
| Texture Fill Rate | 554.4 |
| Manufacturing Process | 5 nm |
| Power Consumption (TDP) | 220 Watt |
| Floating Point Performance | 35.48 TFLOPS |
General Information
5 specs
General Information
5 specs
| Codename | AD104 |
| Architecture | Ada Lovelace (2022−2024) |
| Launch Price | $599 |
| Release Date | January 8 2024 |
| Performance Ranking Position | 18 |
Similar Performance
Graphics cards with benchmark scores closest to the current hardware, grouped by manufacturer.
NVIDIA (12)
AMD (12)
Our Recommendation for GeForce RTX 4070 SUPER
Suggested pairings based on performance balance
Minimum (Avoid Bottleneck) (12)
Recommended (Balanced) (12)
Popular Comparisons
Compare GeForce RTX 4070 SUPER with other popular GPUs
Compare GeForce RTX 4070 SUPER
See how this GPU stacks up against similar alternatives
Better Alternatives (8)
Similar or Lower Performance (8)
