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
1245-1477 MHz (configurable)
TGP
30-45 W (configurable)
Architecture
Ampere
Benchmarks
Rating
26
Gaming
14
Render
20
Energy
75
TFLOPS (FP32)
5.1-6
Geekbench OpenCL
42,967
3DMarkTime Spy
3932
Steel Nomad Lite Score
3967
GB6 Compute Score
42,967
G3D Mark Score
7720
Blender GPU
752.18
GB6 ML Single Precision
7807
GB6 ML Half Precision
14,632
GB6 ML Quantized
5491
FLOPS (FP32)
5.1-6 TFLOPS
Memory Bandwidth
112 GB/s
3D Mark
Time Spy
3932
Solar Bay
19,073
Port Royal
413
Fire Strike
10,472
Wild Life Extreme
7222
Night Raid
45,365
GeekBench 6 OpenCL
Background Blur
73.3 img/sec
Face Detection
39.7 img/sec
Horizon Detection
1.65 Gpixels/sec
Edge Detection
2.13 Gpixels/sec
Gaussian Blur
2.06 Gpixels/sec
Feature Matching
0.55 Gpixels/sec
Stereo Matching
191.1 Gpixels/sec
Particle Physics
5921.5 FPS
API
OpenCL
Passmark Graphics
G2D Mark
479
DirectX 11
47 FPS
DirectX 12
42 FPS
GPU Compute
3507 Ops/s
GeekBench 6 ML
Image Classification (SP)
3489
Image Segmentation (HP)
7528
Image Super Resolution (Q)
6509
Face Detection (HP)
13,217
Pose Estimation (Q)
24,531
Text Classification (SP)
2148
Machine Translation (HP)
2764
Object Detection (SP)
3948
Depth Estimation (Q)
13,355
Style Transfer (SP)
60,626
Framework
ONNX
Backend
DirectML
General
Vendor
Nvidia
Build
Discrete
Released
December 17, 2021
Case
Laptop
Purpose
Gaming
Segment
Mid-range
Architecture
Ampere
GPU Codename
GA107
Recommended CPU
- Intel Core i5 11500H or above
Graphics Processing Unit
Base Clock
735-1185 MHz (configurable)
Boost Clock
1245-1477 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
64KB per cluster
L2 Cache
2MB shared
Instructions Per Cycle
2 IPC
Raw Performance
Pixel Fill Rate
40-47 GPixel/s
Texture Fill Rate
80-95 GTexel/s
Physical
Interface
PCIe 3.0 x8
TGP
30-45 W (configurable)
Manufacturing
Samsung
Fabrication Process
8 nm
Die Size
200 mm²
Transistor Count
8 billion
Transistor Density
40 MTr/mm²
Memory
Memory Type
GDDR6
Memory Size
4 GB
Memory Clock
1750 MHz
Effective Memory Speed
14000 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
No
DisplayPort
1.4a