GeForce RTX 2070
Technical Highlights
About this GPU Card
GeForce RTX 2070 is a discrete graphics card from NVIDIA released on October 17, 2018 based on the Turing architecture with 8 GB GDDR6 memory. It runs at 1410 MHz base clock, reaches up to 1620 MHz boost clock, and has a 175 W power rating. It supports DirectX 12, Vulkan 1.3, and OpenGL 4.6.
Overall Score Of GeForce RTX 2070
This summarizes how GeForce RTX 2070 scores across key areas like gaming, rendering, AI, and Energy Efficiency.
General Info of GeForce RTX 2070
Vendor
NVIDIA
Release Date
October 17, 2018
Foundry
TSMC
Architecture
Turing
Process Size
12 nm
Transistors
10.8 billion
Launch Price
599
Graphics Processor of GeForce RTX 2070
Base Clock
1410 MHz
Boost Clock
1620 MHz
Shading Units
2304
Compute Units
36
Ray Tracing Cores (RTCs)
36
Tensor Cores
Good288
Textured Mapping Units (TMUs)
144
Render Output Units (ROPs)
64
Die Size
445 mm²
Density
22.47 MTr/mm²
L1 Cache
64 KB (per cluster)
L2 Cache
4 MB
Raw Performance of GeForce RTX 2070
Pixel Fill Rate
104 GPixel/s
Texture Fill Rate
233 GTexel/s
FP32 Performance
7.5 TFLOPs
Memory of GeForce RTX 2070
Memory Size
Good8 GB
Memory Type
GoodGDDR6
Bus Width
256-bit
Memory Clock
Good1750 MHz
Effective Speed
14000 Mbps
Bandwidth
448 GB/s
Board Design of GeForce RTX 2070
Bus Interface
GoodPCIe 3.0 x16
PCIe Version
Good3.0
PCIe Lanes
16
TGP
175 W
APIs of GeForce RTX 2070
DirectX
Good12
OpenGL
Top tier4.6
OpenCL
Top tier3.0
Vulkan
Top tier1.3
HDMI
Good2.0b
DisplayPort
Excellent1.4a
CUDA
7.5
Ray Tracing
1
DLSS
DLSS 2
Benchmarks of GeForce RTX 2070
3D Mark
A standardized suite that approximates real-world gaming workloads to compare graphics performance.
GeekBench 6 OpenCL
GPU compute benchmark focused on workloads like image processing and parallel compute tasks.
Passmark Graphics
A multi-test benchmark that evaluates raster, memory bandwidth, and compute performance.
GFXBench 5
Graphics benchmark using modern GPU APIs and game-like scenes across multiple workloads.
Blender
Rendering performance benchmark using Blender Cycles throughput as a practical content-creation metric.
GeekBench 6 ML
AI benchmark measuring common ML workloads like classification, detection, and super resolution.
FurMark
Stress test designed to push sustained load for thermal stability and cooling behavior.
Performance Charts Of GeForce RTX 2070
These charts give a quick view of FPS scaling across resolutions and how this GPU compares against market top benchmark values.
Gaming FPS Analysis
Performance Benchmarks
Try to Compare GeForce RTX 2070 With Another GPU
More GPUs You Might Like to See
If you are still deciding, these are great options to look at next.
Frequently Asked Questions about GeForce RTX 2070
The GeForce RTX 2070 was officially released in October 17, 2018. It was launched as a graphics solution by NVIDIA.
The GeForce RTX 2070 scores 9,079 on 3DMark Time Spy, indicating its solid capabilities in modern gaming scenarios. This benchmark is the industry standard for measuring DirectX 12 gaming performance.
The GeForce RTX 2070 is equipped with 8 GB of VRAM, which is currently the sweet spot for smooth 1440p gaming and modern texture quality.
The GeForce RTX 2070 has a Total Graphics Power (TGP) of 175 W. This value dictates your power supply (PSU) requirements, so ensure your system can handle this draw effectively.
The GeForce RTX 2070 operates at a base clock speed of 1410 MHz. This is the minimum clock frequency the graphics card runs at under standard workloads before boosting.
The GeForce RTX 2070 features a boost clock speed of 1620 MHz. This clock speed represents the maximum frequency the graphics card can dynamically reach during intense gaming or rendering workloads.
The GeForce RTX 2070 is built on the Turing architecture. This foundational design determines the GPU's power efficiency and support for modern features like hardware Ray Tracing and AI upscaling (DLSS/FSR).
With a performance score of 54%, the GeForce RTX 2070 is ranked as a capable mid-range graphics card in our extensive GPU database.
The GeForce RTX 2070 uses the PCIe 3.0 x16 interface, ensuring high-speed data transfer and minimal bottlenecking between the graphics card and the motherboard.
The GeForce RTX 2070 features 2,304 shading units (cores), which are directly responsible for rendering complex visual effects and lighting in modern games.
The GeForce RTX 2070 contains approximately 10.8 billion transistors, packed into its silicon to deliver massive parallel processing capabilities.
The GeForce RTX 2070 is manufactured on a 12 nm node. A smaller process node generally translates to better energy efficiency and improved thermal management.