Home/Graphics Cards/GeForce RTX 4070 SUPER
GeForce RTX 4070 SUPER
Nvidia Desktop GPU

GeForce RTX 4070 SUPER

62B
Memory12 GB
Memory TypeGDDR6X
Boost Clock2475 MHz
TGP220 W
ArchitectureAda Lovelace
Launch Price$599
⇄ Compare with…

Benchmarks

Gaming64
Render62
TFLOPS (FP32)35.5
Geekbench OpenCL206,598
3DMarkTime Spy20,879
Steel Nomad Lite Score21,566
GB6 Compute Score206,598
Cinebench 2024 GPU20,703
G3D Mark Score29,939
Blender GPU6145.7
GB6 ML Single Precision30,706
GB6 ML Half Precision43,851
GB6 ML Quantized23,776
FLOPS (FP32)35.5 TFLOPS
Memory Bandwidth504.2 GB/s

Full specifications

3D Mark

Time Spy
20879
Solar Bay
98188
Port Royal
13123
Fire Strike
50092
Wild Life Extreme
41625
Night Raid
164614

GeekBench 6 OpenCL

Background Blur
359.5 img/sec
Face Detection
210 img/sec
Horizon Detection
7.61 Gpixels/sec
Edge Detection
10.4 Gpixels/sec
Gaussian Blur
11.3 Gpixels/sec
Feature Matching
1.97 Gpixels/sec
Stereo Matching
969.3 Gpixels/sec
Particle Physics
29061.4 FPS
API
OpenCL

Passmark Graphics

G2D Mark
1193
DirectX 11
271 FPS
DirectX 12
110 FPS
GPU Compute
16925 Ops/s

GeekBench 6 ML

Image Classification (SP)
12146
Image Segmentation (HP)
23932
Image Super Resolution (Q)
36321
Face Detection (HP)
52836
Pose Estimation (Q)
179788
Text Classification (SP)
3371
Machine Translation (HP)
5017
Object Detection (SP)
15164
Depth Estimation (Q)
62500
Style Transfer (SP)
357489
Framework
ONNX
Backend
DirectML

General

Vendor
Nvidia
Build
Discrete
Released
January 17, 2024
Launch price (MSRP)
$599
Case
Desktop
Purpose
Gaming
Segment
Mid-range
Architecture
Ada Lovelace
GPU Codename
AD104
AMD Equivalent
- Radeon RX 7900 XT
Recommended CPU
- Intel Core i7 14700K or above

Graphics Processing Unit

Base Clock
1980 MHz
Boost Clock
2475 MHz
Shading Units
7168
Texture Mapping Units (TMUs)
224
Render Output Units (ROPs)
80
Compute Units (Pipelines)
56
Tensor Cores
224
Ray-tracing Cores
56
L1 Cache
128KB per cluster
L2 Cache
48MB shared
Instructions Per Cycle
2 IPC

Raw Performance

Pixel Fill Rate
198 GPixel/s
Texture Fill Rate
554 GTexel/s

Physical

Interface
PCIe 4.0 x16
TGP
220 W
Manufacturing
TSMC
Fabrication Process
5 nm
Die Size
294 mm²
Transistor Count
35 billion
Transistor Density
119.05 MTr/mm²

Memory

Memory Type
GDDR6X
Memory Size
12 GB
Memory Clock
1313 MHz
Effective Memory Speed
21000 Mbps
Bus
192-bit
ECC
No

API

DirectX
12
Vulkan
1.3
OpenGL
4.6
OpenCL
3.0
CUDA
8.9
Ray Tracing
Yes
DLSS
DLSS 3
DisplayPort
1.4a

Specifications compiled from NanoReview. Last updated 2026-09-29.

More graphics cards

View all →
97
Nvidia RTX Pro 6000 Blackwell
Nvidia

Nvidia RTX Pro 6000 Blackwell

  • Memory96 GB
  • Memory TypeGDDR7
  • Boost Clock2617 MHz
  • TGP600 W
Desktop GPU
96
GeForce RTX 5090
Nvidia

GeForce RTX 5090

  • Memory32 GB
  • Memory TypeGDDR7
  • Boost Clock2407 MHz
  • TGP575 W
Desktop GPU
89
GeForce RTX 4090
Nvidia

GeForce RTX 4090

  • Memory24 GB
  • Memory TypeGDDR6X
  • Boost Clock2520 MHz
  • TGP450 W
Desktop GPU
84
GeForce RTX 5080
Nvidia

GeForce RTX 5080

  • Memory16 GB
  • Memory TypeGDDR7
  • Boost Clock2617 MHz
  • TGP360 W
Desktop GPU