Head to head
Compare Graphics Cards
Pick up to 4. Winners are highlighted in green ▲.
1 selected
Key specs
Memory
32 GB
Memory Type
GDDR6
Boost Clock
2550 MHz
TGP
250 W
Architecture
Ada Lovelace
Launch Price
$4000
Benchmarks
Rating
73
Gaming
72
Render
83
TFLOPS (FP32)
65.3
Geekbench OpenCL
260,099
3DMarkTime Spy
18,364
Steel Nomad Lite Score
28,751
GB6 Compute Score
260,099
G3D Mark Score
30,950
Blender GPU
7698.51
GB6 ML Single Precision
24,715
GB6 ML Half Precision
36,753
GB6 ML Quantized
19,649
FLOPS (FP32)
65.3 TFLOPS
Memory Bandwidth
576 GB/s
3D Mark
Time Spy
18,364
Solar Bay
128,428
Port Royal
17,986
Fire Strike
49,922
Wild Life Extreme
52,866
Night Raid
139,369
GeekBench 6 OpenCL
Background Blur
286.6 img/sec
Face Detection
220.4 img/sec
Horizon Detection
9.93 Gpixels/sec
Edge Detection
13.7 Gpixels/sec
Gaussian Blur
18.9 Gpixels/sec
Feature Matching
2.2 Gpixels/sec
Stereo Matching
1580 Gpixels/sec
Particle Physics
41235.6 FPS
API
OpenCL
Passmark Graphics
G2D Mark
1008
DirectX 11
272 FPS
DirectX 12
110 FPS
GPU Compute
20805 Ops/s
GeekBench 6 ML
Image Classification (SP)
9943
Image Segmentation (HP)
19,696
Image Super Resolution (Q)
32,252
Face Detection (HP)
43,098
Pose Estimation (Q)
138,689
Text Classification (SP)
2893
Machine Translation (HP)
4064
Object Detection (SP)
12,467
Depth Estimation (Q)
50,352
Style Transfer (SP)
265,482
Framework
ONNX
Backend
DirectML
General
Vendor
Nvidia
Build
Discrete
Released
August 9, 2023
Launch price (MSRP)
$4000
Case
Desktop
Purpose
Professional
Segment
High-end
Architecture
Ada Lovelace
GPU Codename
AD102
Recommended CPU
- Intel Core i9 14900K or above
Graphics Processing Unit
Base Clock
1155 MHz
Boost Clock
2550 MHz
Shading Units
12,800
Texture Mapping Units (TMUs)
400
Render Output Units (ROPs)
176
Compute Units (Pipelines)
100
Tensor Cores
400
Ray-tracing Cores
100
L1 Cache
128KB per cluster
L2 Cache
72MB shared
Instructions Per Cycle
2 IPC
Raw Performance
Pixel Fill Rate
449 GPixel/s
Texture Fill Rate
1020 GTexel/s
Physical
Interface
PCIe 4.0 x16
TGP
250 W
Manufacturing
TSMC
Fabrication Process
5 nm
Die Size
609 mm²
Transistor Count
76 billion
Transistor Density
124.79 MTr/mm²
Memory
Memory Type
GDDR6
Memory Size
32 GB
Memory Clock
2250 MHz
Effective Memory Speed
18000 Mbps
Bus
256-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