Head to head
Compare Graphics Cards
Pick up to 4. Winners are highlighted in green ▲.
1 selected
Key specs
Memory
12 GB
Memory Type
GDDR6
Boost Clock
1465-2260 MHz (configurable)
TGP
60-175 W (configurable)
Architecture
Ada Lovelace
Benchmarks
Rating
51
Gaming
51
Render
57
Energy
44
TFLOPS (FP32)
21.8-33.6
Geekbench OpenCL
139,462
3DMarkTime Spy
15,498
Steel Nomad Lite Score
16,980
GB6 Compute Score
139,462
Cinebench 2024 GPU
16,483
G3D Mark Score
21,965
Blender GPU
5009.03
GB6 ML Single Precision
22,488
GB6 ML Half Precision
35,441
GB6 ML Quantized
16,689
FLOPS (FP32)
21.8-33.6 TFLOPS
Memory Bandwidth
432 GB/s
3D Mark
Time Spy
15,498
Solar Bay
67,951
Port Royal
10,118
Fire Strike
36,295
Night Raid
130,940
GeekBench 6 OpenCL
Background Blur
187.1 img/sec
Face Detection
139.5 img/sec
Horizon Detection
5.71 Gpixels/sec
Edge Detection
8.53 Gpixels/sec
Gaussian Blur
8.38 Gpixels/sec
Feature Matching
1.55 Gpixels/sec
Stereo Matching
577.7 Gpixels/sec
Particle Physics
16849 FPS
API
OpenCL
Passmark Graphics
G2D Mark
714
DirectX 11
214 FPS
DirectX 12
96 FPS
GPU Compute
8532 Ops/s
GeekBench 6 ML
Image Classification (SP)
8658
Image Segmentation (HP)
17,759
Image Super Resolution (Q)
28,281
Face Detection (HP)
37,971
Pose Estimation (Q)
113,009
Text Classification (SP)
3535
Machine Translation (HP)
4038
Object Detection (SP)
11,288
Depth Estimation (Q)
38,963
Style Transfer (SP)
236,141
Framework
ONNX
Backend
DirectML
General
Vendor
Nvidia
Build
Discrete
Released
March 21, 2023
Case
Laptop
Purpose
Professional
Segment
High-end
Architecture
Ada Lovelace
GPU Codename
AD104
Recommended CPU
- Intel Core Ultra 9 185H or above
Graphics Processing Unit
Boost Clock
1465-2260 MHz (configurable)
Shading Units
7424
Texture Mapping Units (TMUs)
232
Render Output Units (ROPs)
80
Compute Units (Pipelines)
58
Tensor Cores
232
Ray-tracing Cores
58
L1 Cache
128KB per cluster
L2 Cache
48MB shared
Instructions Per Cycle
2 IPC
Raw Performance
Pixel Fill Rate
117-181 GPixel/s
Texture Fill Rate
340-524 GTexel/s
Physical
Interface
PCIe 4.0 x16
TGP
60-175 W (configurable)
Manufacturing
TSMC
Fabrication Process
5 nm
Die Size
294 mm²
Transistor Count
35.8 billion
Transistor Density
121.77 MTr/mm²
Max. Temperature
95°C
Memory
Memory Type
GDDR6
Memory Size
12 GB
Memory Clock
2250 MHz
Effective Memory Speed
18000 Mbps
Bus
192-bit
ECC
Yes
API
DirectX
12
Vulkan
1.3
OpenGL
4.6
OpenCL
3.0
CUDA
8.9
Ray Tracing
Yes
DLSS
DLSS 3
DisplayPort
1.4a