Nvidia GeForce RTX 4070

Nvidia GeForce RTX 4070
  • Brand: Nvidia
  • Cores: 5888
  • Form Factor: PC use
  • Use case: Gaming
  • Announced: April, 13, 2023

Review

Games
Performance in DirectX, OpenCL, Vulkan
AI/ML
AI workload testing
Professional Apps
3D modeling, video editing, rendering
Energy Efficiency
Power usage in various scenarios
NanoReview Score
Overall score by NanoReview

Benchmark Tests

Performance comparison across tasks for Nvidia GeForce RTX 4070

Games

FPS Table
Game title
1080p (High)
1080p (Ultra)
1440p (Ultra)
4K (Ultra)
Forza Horizon 5
170
113
105
79
The Witcher 3
191
160
114
61
Counter-Strike 2
262
207
148
82
Far Cry 6
148
135
112
71
Hogwarts Legacy
120
96
78
43
COD Modern Warfare 3
154
141
110
72
Ghost of Tsushima
104
87
74
40
Cyberpunk 2077
133
115
78
34
Shadow of the Tomb Raider
209
194
148
81
Avg FPS
1080p High166
1080p Ultra139
1440p Ultra107
4K Ultra63
DeviationLow

Benchmarks

CPU performance comparison across tasks
3DMark
Steel Nomad Lite Score
Nvidia GeForce RTX 4070
18116
Time Spy17825
Solar Bay82645
Port Royal11149
Fire Strike44109
Night Raid152587
GeekBench v6
GB6 Compute Score
Nvidia GeForce RTX 4070
167522
Background Blur233 frames/s
Face Detection141.7 frames/s
Horizon Detection6.62 Gpix/sec
Edge Detection9.19 Gpix/sec
Gaussian Blur9.2 Gpix/sec
Feature Matching1.78 Gpix/sec
Stereo Matching845.4 Gpix/sec
Particle Physics25043.9 fps
APIOpenCL
PassMark
PassMark Graphics
Nvidia GeForce RTX 4070
26962
G2D Mark1165
DirectX 11245 fps
DirectX 12102 fps
GPU Compute14820 Ops/s
GFXBench 5
Aztec Ruins (High 4K)
Nvidia GeForce RTX 4070
192 fps
Aztec Ruins (Normal)1039 fps
Car Chase900 fps
Manhattan 3.1.1 (1440p)761.2 fps
T-Rex3848.1 fps
ALU 25980.8 fps
Driver Overhead 2296.7 fps
APIOpenGL
OSWindows
Tessellation6200.7

Tech Specs

Specs & test comparison

General Info

Manufacturer Nvidia
Build Discrete
Announced April, 13, 2023
Form Factor PC use
Use case Gaming
Segment Mid-range
Architecture Ada Lovelace
Codename AD104
Price 599

GPU

GPU Frequency 1920 MHz
Boost GPU Frequency 2475 MHz
Shader Units 5888
TMUs 184
ROPs 64
Execution Units 46
Ray Tracing Cores 46
Tensor Cores 184
L1 cache 128 KB/core
L2 cache 36000 KB/core
Instructions per Clock 2 IPC

Performance

Pixel Fill Rate 158 Gpix/sec
Texture Fill Rate 455 GTex/s
FLOPS 29.1 TFLOPS

Process

Interface PCIe 4.0 x16
TGP 200 W
Process TSMC
Process tech. 5 nm
Transistor Size 294 mm²
Transistor count 35 billion
Transistor density 119.05 MTr/mm²

Memory

Interface GDDR6X
Memory Frequency 1313 MHz
Bus 192 bit
ECC support No
Effective Memory Speed 21000 MB/s
Memory Size 12 GB
Max Throughput
Nvidia GeForce RTX 4070
504.2 GB/s

API

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

User Rating

2.5 out 5 Points (2 Votes)

Comments (0)