Head to head
Compare Graphics Cards
Pick up to 4. Winners are highlighted in green ▲.
1 selected
Key specs
Memory
16 GB
Memory Type
GDDR6
Boost Clock
1050-1663 MHz (configurable)
TGP
80-165 W (configurable)
Architecture
Ampere
Benchmarks
Rating
40
Gaming
33
Render
56
Energy
40
TFLOPS (FP32)
15.6-24.7
Geekbench OpenCL
144,566
3DMarkTime Spy
8914
Steel Nomad Lite Score
9139
GB6 Compute Score
144,566
G3D Mark Score
17,305
Blender GPU
2868.13
GB6 ML Single Precision
15,704
GB6 ML Half Precision
26,550
GB6 ML Quantized
9885
FLOPS (FP32)
15.6-24.7 TFLOPS
Memory Bandwidth
512 GB/s
3D Mark
Time Spy
8914
Solar Bay
31,554
Port Royal
5890
Fire Strike
24,599
Wild Life Extreme
16,879
Night Raid
27,155
GeekBench 6 OpenCL
Background Blur
222.1 img/sec
Face Detection
132.2 img/sec
Horizon Detection
6.83 Gpixels/sec
Edge Detection
9.64 Gpixels/sec
Gaussian Blur
7.81 Gpixels/sec
Feature Matching
1.27 Gpixels/sec
Stereo Matching
615.9 Gpixels/sec
Particle Physics
18134.8 FPS
API
OpenCL
Passmark Graphics
G2D Mark
727
DirectX 11
131 FPS
DirectX 12
85 FPS
GPU Compute
7491 Ops/s
GeekBench 6 ML
Image Classification (SP)
6982
Image Segmentation (HP)
15,050
Image Super Resolution (Q)
14,412
Face Detection (HP)
27,475
Pose Estimation (Q)
66,491
Text Classification (SP)
2852
Machine Translation (HP)
3306
Object Detection (SP)
8121
Depth Estimation (Q)
24,442
Style Transfer (SP)
156,421
Framework
ONNX
Backend
DirectML
General
Vendor
Nvidia
Build
Discrete
Released
March 30, 2022
Case
Laptop
Purpose
Professional
Segment
High-end
Architecture
Ampere
GPU Codename
GA103
Successor
- Nvidia RTX 5000 Laptop (Ada)
Recommended CPU
- Intel Core i9 12900HX or above
Graphics Processing Unit
Boost Clock
1050-1663 MHz (configurable)
Shading Units
7424
Texture Mapping Units (TMUs)
232
Render Output Units (ROPs)
96
Compute Units (Pipelines)
58
Tensor Cores
232
Ray-tracing Cores
58
L1 Cache
128KB per cluster
L2 Cache
4MB shared
Instructions Per Cycle
2 IPC
Raw Performance
Pixel Fill Rate
101-160 GPixel/s
Texture Fill Rate
244-386 GTexel/s
Physical
Interface
PCIe 4.0 x16
TGP
80-165 W (configurable)
Manufacturing
Samsung
Fabrication Process
8 nm
Die Size
496 mm²
Transistor Count
22 billion
Transistor Density
44.35 MTr/mm²
Memory
Memory Type
GDDR6
Memory Size
16 GB
Memory Clock
2000 MHz
Effective Memory Speed
16000 Mbps
Bus
256-bit
ECC
Yes
API
DirectX
12
Vulkan
1.3
OpenGL
4.6
OpenCL
3.0
CUDA
8.6
Ray Tracing
Yes
DLSS
DLSS 2
DisplayPort
1.4