Nvidia RTX 4000 Ada

Nvidia RTX 4000 Ada
  • Graphics Processor: AD104
  • Cores: 6144
  • TMUs / ROPs: 192 / 80

Review

Gaming
47
Workstation
52
AI/ML
44
Energy Efficiency
58
NanoReview Final Score
48
Compare Nvidia RTX 4000 Ada with other GPUs

Games

FPS Table
Forza Horizon 5
149
98
91
63
The Witcher 3
177
143
103
54
Counter-Strike 2
253
201
135
80
Far Cry 6
131
123
101
58
Hogwarts Legacy
102
82
66
34
CoD: Modern Warfare III
126
119
88
56
Ghost of Tsushima
94
79
61
33
Cyberpunk 2077
112
96
64
30
Shadow of the Tomb Raider
175
157
119
65
Average FPS by Resolution
1080p High 147
1080p Ultra 122
1440p Ultra 92
4K Ultra 53
Margin of Error High

Test in Benchmarks

Performance tests in graphics benchmarks and applications

3D Mark

Multiplatform graphics benchmark suite that directly correlates with performance in modern games
Steel Nomad Lite Score
14674
Time Spy 14438
Solar Bay 65875
Port Royal 8974
Fire Strike 37396
Night Raid 158480
Sources: 3DMark [1]

GeekBench 6 OpenCL

GPU test for computational tasks (image processing, photography, computer vision, and ML)
GB6 Compute Score
151680
Background Blur 235.3 img/sec
Face Detection 157.9 img/sec
Horizon Detection 5.53 Gpixels/sec
Edge Detection 7.44 Gpixels/sec
Gaussian Blur 7.87 Gpixels/sec
Feature Matching 1.58 Gpixels/sec
Stereo Matching 737.7 Gpixels/sec
Particle Physics 22409.2 FPS
API OpenCL
Sources: Geekbench [3]

Passmark Graphics

Videocard test that focuses on compute shaders, multi-texturing, tessellation, and other features
G3D Mark Score
23646
G2D Mark 1110
DirectX 11 203 FPS
DirectX 12 93 FPS
GPU Compute 11869 Ops/s
Sources: PassMark [5] – 1138 samples

Blender

Rendering performance test for 3D modeling
Blender GPU
4447.56
Sources: Blender [9] – 70 samples

Artificial Intelligence Tests

Performance in machine learning and artificial intelligence tasks

GeekBench 6 ML

Tests throughput of AI operations in single, half, and quantized precision
GB6 ML Single Precision
22372
GB6 ML Half Precision
35651
GB6 ML Quantized
17081
Image Classification (SP) 9717
Image Segmentation (HP) 19365
Image Super Resolution (Q) 29227
Face Detection (HP) 40416
Pose Estimation (Q) 105639
Text Classification (SP) 3577
Machine Translation (HP) 4193
Object Detection (SP) 10820
Depth Estimation (Q) 36574
Style Transfer (SP) 200936
Framework ONNX
Backend DirectML
Sources: Geekbench [9]

Specifications

Detailed technical specifications of the Nvidia RTX 4000 Ada

General

Vendor Nvidia
Build Discrete
Released August 9, 2023
Launch price (MSRP) $1250
Case Desktop
Purpose Gaming
Segment High-end
Architecture Ada Lovelace
GPU Codename AD104
Recommended CPU - Intel Core i7 14700K or above
Desktop GPU rating - 35th place

Graphics Processing Unit

Base Clock 1500 MHz
Boost Clock 2175 MHz
Shading Units 6144
Texture Mapping Units (TMUs) 192
Render Output Units (ROPs) 80
Compute Units (Pipelines) 48
Tensor Cores 192
Ray-tracing Cores 48
L1 Cache 128KB per cluster
L2 Cache 48MB shared
Instructions Per Cycle 2 IPC

Raw Performance

Pixel Fill Rate 174 GPixel/s
Texture Fill Rate 418 GTexel/s
FLOPS (FP32)
26.7 TFLOPS

Physical

Interface PCIe 4.0 x16
TGP 130 W
Manufacturing TSMC
Fabrication Process 5 nm
Die Size 294 mm²
Transistor Count 35 billion
Transistor Density 119.05 MTr/mm²

Memory

Memory Type GDDR6
Memory Size 20 GB
Memory Clock 2250 MHz
Effective Memory Speed 18000 Mbps
Bus 160-bit
ECC No
Memory Bandwidth
360 GB/s

API

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

Comments

Do you have any questions about RTX 4000 Ada? Please, use comment form below
🌐 Register your profile and become part of NanoReview community!