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
745-1710 MHz (configurable)
TGP
20-60 W (configurable)
Architecture
Ampere
Benchmarks
Rating
25
Gaming
13
Render
23
Energy
71
TFLOPS (FP32)
3.1-7
Geekbench OpenCL
40,574
3DMarkTime Spy
3022
Steel Nomad Lite Score
3026
GB6 Compute Score
40,574
G3D Mark Score
6546
Blender GPU
675.13
GB6 ML Single Precision
7597
GB6 ML Half Precision
15,030
GB6 ML Quantized
5337
FLOPS (FP32)
3.1-7 TFLOPS
Memory Bandwidth
96 GB/s
3D Mark
Time Spy
3022
Solar Bay
13,710
Port Royal
625
Fire Strike
10,265
Wild Life Extreme
4053
Night Raid
38,312
GeekBench 6 OpenCL
Background Blur
62.4 img/sec
Face Detection
35.7 img/sec
Horizon Detection
1.62 Gpixels/sec
Edge Detection
2.11 Gpixels/sec
Gaussian Blur
2.05 Gpixels/sec
Feature Matching
0.52 Gpixels/sec
Stereo Matching
185.1 Gpixels/sec
Particle Physics
5502.5 FPS
API
OpenCL
Passmark Graphics
G2D Mark
411
DirectX 11
40 FPS
DirectX 12
38 FPS
GPU Compute
2901 Ops/s
GeekBench 6 ML
Image Classification (SP)
3298
Image Segmentation (HP)
8358
Image Super Resolution (Q)
6219
Face Detection (HP)
14,319
Pose Estimation (Q)
22,995
Text Classification (SP)
2226
Machine Translation (HP)
3163
Object Detection (SP)
3768
Depth Estimation (Q)
12,079
Style Transfer (SP)
53,139
Framework
ONNX
Backend
DirectML
General
Vendor
Nvidia
Build
Discrete
Released
March 22, 2022
Case
Laptop
Purpose
Professional
Segment
Entry-level
Architecture
Ampere
GPU Codename
GA107S
Recommended CPU
- Intel Core i7 12700H or above
Graphics Processing Unit
Base Clock
370-890 MHz (configurable)
Boost Clock
745-1710 MHz (configurable)
Shading Units
2048
Texture Mapping Units (TMUs)
64
Render Output Units (ROPs)
32
Compute Units (Pipelines)
16
Tensor Cores
64
Ray-tracing Cores
16
L1 Cache
128KB per cluster
L2 Cache
2MB shared
Instructions Per Cycle
2 IPC
Raw Performance
Pixel Fill Rate
24-55 GPixel/s
Texture Fill Rate
48-109 GTexel/s
Physical
Interface
PCIe 4.0 x8
TGP
20-60 W (configurable)
Manufacturing
Samsung
Fabrication Process
8 nm
Die Size
200 mm²
Transistor Count
8.7 billion
Transistor Density
43.5 MTr/mm²
Memory
Memory Type
GDDR6
Memory Size
4 GB
Memory Clock
1500 MHz
Effective Memory Speed
12000 Mbps
Bus
64-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