Head to head

Compare Graphics Cards

Pick up to 4. Winners are highlighted in green ▲.

Key specs
Memory
16 GB
Memory Type
GDDR6
Boost Clock
1245-1770 MHz (configurable)
TGP
80-165 W (configurable)
Architecture
Ampere
Benchmarks
Rating
39
Gaming
33
Render
50
Energy
39
TFLOPS (FP32)
15.3-21.7
Geekbench OpenCL
111,855
3DMarkTime Spy
9295
Steel Nomad Lite Score
9479
GB6 Compute Score
111,855
G3D Mark Score
16,354
Blender GPU
2889.33
GB6 ML Single Precision
15,655
GB6 ML Half Precision
24,490
GB6 ML Quantized
10,684
FLOPS (FP32)
15.3-21.7 TFLOPS
Memory Bandwidth
448 GB/s
3D Mark
Time Spy
9295
Solar Bay
40,186
Port Royal
5817
Fire Strike
26,200
Wild Life Extreme
20,653
Night Raid
61,009
GeekBench 6 OpenCL
Background Blur
172.7 img/sec
Face Detection
103.8 img/sec
Horizon Detection
5.34 Gpixels/sec
Edge Detection
7.2 Gpixels/sec
Gaussian Blur
5.61 Gpixels/sec
Feature Matching
1.05 Gpixels/sec
Stereo Matching
474.4 Gpixels/sec
Particle Physics
14218.2 FPS
API
OpenCL
Passmark Graphics
G2D Mark
663
DirectX 11
138 FPS
DirectX 12
74 FPS
GPU Compute
6941 Ops/s
GeekBench 6 ML
Image Classification (SP)
6590
Image Segmentation (HP)
12,226
Image Super Resolution (Q)
16,682
Face Detection (HP)
30,795
Pose Estimation (Q)
71,291
Text Classification (SP)
2115
Machine Translation (HP)
3207
Object Detection (SP)
8583
Depth Estimation (Q)
25,256
Style Transfer (SP)
149,822
Framework
ONNX
Backend
DirectML
General
Vendor
Nvidia
Build
Discrete
Released
April 12, 2021
Case
Laptop
Purpose
Professional
Segment
High-end
Architecture
Ampere
GPU Codename
GA104
Recommended CPU
- Intel Core i9 12900HX or above
Graphics Processing Unit
Base Clock
780-1215 MHz (configurable)
Boost Clock
1245-1770 MHz (configurable)
Shading Units
6144
Texture Mapping Units (TMUs)
192
Render Output Units (ROPs)
96
Compute Units (Pipelines)
48
Tensor Cores
192
Ray-tracing Cores
48
L1 Cache
128KB per cluster
L2 Cache
4MB shared
Instructions Per Cycle
2 IPC
Raw Performance
Pixel Fill Rate
120-170 GPixel/s
Texture Fill Rate
239-340 GTexel/s
Physical
Interface
PCIe 4.0 x16
TGP
80-165 W (configurable)
Manufacturing
Samsung
Fabrication Process
8 nm
Die Size
392 mm²
Transistor Count
17.4 billion
Transistor Density
44.39 MTr/mm²
Memory
Memory Type
GDDR6
Memory Size
16 GB
Memory Clock
1750 MHz
Effective Memory Speed
14000 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
1.4a