Head to head
Compare Graphics Cards
Pick up to 4. Winners are highlighted in green ▲.
1 selected
Key specs
Memory
8 GB
Memory Type
GDDR6
Boost Clock
1290-1620 MHz (configurable)
TGP
80-150 W (configurable)
Architecture
Ampere
Benchmarks
Rating
37
Gaming
34
Render
41
Energy
43
TFLOPS (FP32)
13.2-16.6
Geekbench OpenCL
118,499
3DMarkTime Spy
10,477
Steel Nomad Lite Score
10,216
GB6 Compute Score
118,499
Cinebench 2024 GPU
10,455
G3D Mark Score
15,017
Blender GPU
2973.81
GB6 ML Single Precision
17,250
GB6 ML Half Precision
27,936
GB6 ML Quantized
11,249
FLOPS (FP32)
13.2-16.6 TFLOPS
Memory Bandwidth
448 GB/s
3D Mark
Time Spy
10,477
Solar Bay
45,198
Port Royal
6247
Fire Strike
26,725
Wild Life Extreme
21,132
Night Raid
82,499
GeekBench 6 OpenCL
Background Blur
170.3 img/sec
Face Detection
113.6 img/sec
Horizon Detection
5.59 Gpixels/sec
Edge Detection
7.94 Gpixels/sec
Gaussian Blur
6.19 Gpixels/sec
Feature Matching
1.16 Gpixels/sec
Stereo Matching
467 Gpixels/sec
Particle Physics
15131.3 FPS
API
OpenCL
Passmark Graphics
G2D Mark
626
DirectX 11
137 FPS
DirectX 12
62 FPS
GPU Compute
6642 Ops/s
GeekBench 6 ML
Image Classification (SP)
6969
Image Segmentation (HP)
17,142
Image Super Resolution (Q)
16,426
Face Detection (HP)
31,628
Pose Estimation (Q)
74,413
Text Classification (SP)
2522
Machine Translation (HP)
3639
Object Detection (SP)
9002
Depth Estimation (Q)
27,790
Style Transfer (SP)
160,005
Framework
ONNX
Backend
DirectML
General
Vendor
Nvidia
Build
Discrete
Released
January 12, 2021
Case
Laptop
Purpose
Gaming
Segment
High-end
Architecture
Ampere
GPU Codename
GA104 (GN20-E5)
AMD Equivalent
- Radeon RX 6700M
Successor
- GeForce RTX 5070 Laptop
Recommended CPU
- Intel Core i7 12700H or above
Graphics Processing Unit
Base Clock
780-1215 MHz (configurable)
Boost Clock
1290-1620 MHz (configurable)
Shading Units
5120
Texture Mapping Units (TMUs)
160
Render Output Units (ROPs)
80
Compute Units (Pipelines)
40
Tensor Cores
160
Ray-tracing Cores
40
L1 Cache
128KB per cluster
L2 Cache
4MB shared
Instructions Per Cycle
2 IPC
Raw Performance
Pixel Fill Rate
103-130 GPixel/s
Texture Fill Rate
206-259 GTexel/s
Physical
Interface
PCIe 4.0 x16
TGP
80-150 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
8 GB
Memory Clock
1500-1750 MHz
Effective Memory Speed
12000-14000 Mbps
Bus
256-bit
ECC
No
API
DirectX
12
Vulkan
1.2
OpenGL
4.6
OpenCL
2.0
CUDA
8.6
Ray Tracing
Yes
DLSS
DLSS 2
DisplayPort
1.4a