Head to head
Compare Graphics Cards
Pick up to 4. Winners are highlighted in green ▲.
1 selected
Key specs
Memory
4 GB
Memory Type
GDDR6
Boost Clock
1035-1695 MHz (configurable)
TGP
60-95 W (configurable)
Architecture
Ampere
Benchmarks
Rating
27
Gaming
17
Render
29
Energy
59
TFLOPS (FP32)
5.3-8.7
Geekbench OpenCL
57,201
3DMarkTime Spy
4796
Steel Nomad Lite Score
4434
GB6 Compute Score
57,201
G3D Mark Score
9413
Blender GPU
1233.56
GB6 ML Single Precision
9891
GB6 ML Half Precision
18,270
GB6 ML Quantized
6987
FLOPS (FP32)
5.3-8.7 TFLOPS
Memory Bandwidth
192 GB/s
3D Mark
Time Spy
4796
Solar Bay
19,912
Port Royal
2920
Fire Strike
11,732
Wild Life Extreme
8828
Night Raid
50,295
GeekBench 6 OpenCL
Background Blur
92.8 img/sec
Face Detection
54.2 img/sec
Horizon Detection
2.47 Gpixels/sec
Edge Detection
3.32 Gpixels/sec
Gaussian Blur
2.63 Gpixels/sec
Feature Matching
0.7 Gpixels/sec
Stereo Matching
236.9 Gpixels/sec
Particle Physics
7148.8 FPS
API
OpenCL
Passmark Graphics
G2D Mark
508
DirectX 11
64 FPS
DirectX 12
47 FPS
GPU Compute
4222 Ops/s
GeekBench 6 ML
Image Classification (SP)
4240
Image Segmentation (HP)
9190
Image Super Resolution (Q)
9374
Face Detection (HP)
18,335
Pose Estimation (Q)
36,989
Text Classification (SP)
2035
Machine Translation (HP)
2687
Object Detection (SP)
5174
Depth Estimation (Q)
16,537
Style Transfer (SP)
77,854
Framework
ONNX
Backend
DirectML
General
Vendor
Nvidia
Build
Discrete
Released
April 12, 2021
Case
Laptop
Purpose
Professional
Segment
Mid-range
Architecture
Ampere
GPU Codename
GA106
Successor
- Nvidia RTX 2000 Laptop (Ada)
Recommended CPU
- Intel Core i7 12800H or above
Graphics Processing Unit
Base Clock
735-1463 MHz (configurable)
Boost Clock
1035-1695 MHz (configurable)
Shading Units
2560
Texture Mapping Units (TMUs)
80
Render Output Units (ROPs)
48
Compute Units (Pipelines)
20
Tensor Cores
80
Ray-tracing Cores
20
L1 Cache
128KB per cluster
L2 Cache
2MB shared
Instructions Per Cycle
2 IPC
Raw Performance
Pixel Fill Rate
50-81 GPixel/s
Texture Fill Rate
83-136 GTexel/s
Physical
Interface
PCIe 4.0 x16
TGP
60-95 W (configurable)
Manufacturing
Samsung
Fabrication Process
8 nm
Die Size
276 mm²
Transistor Count
12 billion
Transistor Density
43.48 MTr/mm²
Memory
Memory Type
GDDR6
Memory Size
4 GB
Memory Clock
1500 MHz
Effective Memory Speed
12000 Mbps
Bus
128-bit
ECC
No
API
DirectX
12
Vulkan
1.3
OpenGL
4.6
OpenCL
3.0
CUDA
8.6
Ray Tracing
Yes
DLSS
DLSS 2
DisplayPort
1.4a